| 1 | InternImage-H | 1478 | No | InternImage: Exploring Large-Scale Vision Founda... | 2022-11-10 | Code |
| 2 | DaViT-G | 1038 | No | DaViT: Dual Attention Vision Transformers | 2022-04-07 | Code |
| 3 | SWAG (ViT H/14) | 1018.8 | No | Revisiting Weakly Supervised Pre-Training of Vis... | 2022-01-20 | Code |
| 4 | MViTv2-H (512 res, ImageNet-21k pretrain) | 763.5 | No | MViTv2: Improved Multiscale Vision Transformers ... | 2021-12-02 | Code |
| 5 | Perceiver (FF) | 707.2 | No | Perceiver: General Perception with Iterative Att... | 2021-03-04 | Code |
| 6 | MOAT-4 22K+1K | 648.5 | No | MOAT: Alternating Mobile Convolution and Attenti... | 2022-10-04 | Code |
| 7 | DY-MobileNetV2 ×1.0 | 626 | No | Dynamic Convolution: Attention over Convolution ... | 2019-12-07 | Code |
| 8 | FixEfficientNet-L2 | 585 | No | Fixing the train-test resolution discrepancy: Fi... | 2020-03-18 | Code |
| 9 | MambaVision-L3 | 489.1 | No | MambaVision: A Hybrid Mamba-Transformer Vision B... | 2024-07-10 | Code |
| 10 | ELSA-VOLO-D5 (512*512) | 437 | No | ELSA: Enhanced Local Self-Attention for Vision T... | 2021-12-23 | Code |
| 11 | XCiT-L24 | 417.9 | No | XCiT: Cross-Covariance Image Transformers | 2021-06-17 | Code |
| 12 | VOLO-D5+HAT | 412 | No | Improving Vision Transformers by Revisiting High... | 2022-04-03 | Code |
| 13 | VOLO-D5 | 412 | No | VOLO: Vision Outlooker for Visual Recognition | 2021-06-24 | Code |
| 14 | CaiT-M-48-448 | 377.3 | No | Going deeper with Image Transformers | 2021-03-31 | Code |
| 15 | NFNet-F6 w/ SAM | 377.28 | No | High-Performance Large-Scale Image Recognition W... | 2021-02-11 | Code |
| 16 | NFNet-F4+ | 367 | No | High-Performance Large-Scale Image Recognition W... | 2021-02-11 | Code |
| 17 | DaViT-H | 334 | No | DaViT: Dual Attention Vision Transformers | 2022-04-07 | Code |
| 18 | ResNeXt-101 32x48d | 306 | No | Exploring the Limits of Weakly Supervised Pretra... | 2018-05-02 | Code |
| 19 | NFNet-F5 w/ SAM | 289.76 | No | High-Performance Large-Scale Image Recognition W... | 2021-02-11 | Code |
| 20 | NFNet-F5 | 289.76 | No | High-Performance Large-Scale Image Recognition W... | 2021-02-11 | Code |
| 21 | MOAT-3 1K only | 271 | No | MOAT: Alternating Mobile Convolution and Attenti... | 2022-10-04 | Code |
| 22 | CAIT-M36-448 | 247.8 | No | Going deeper with Image Transformers | 2021-03-31 | Code |
| 23 | NFNet-F4 | 215.24 | No | High-Performance Large-Scale Image Recognition W... | 2021-02-11 | Code |
| 24 | LV-ViT-L | 214.8 | No | All Tokens Matter: Token Labeling for Training B... | 2021-04-22 | Code |
| 25 | AmoebaNet-A | 208 | No | Regularized Evolution for Image Classifier Archi... | 2018-02-05 | Code |
| 26 | VOLO-D4 | 197 | No | VOLO: Vision Outlooker for Visual Recognition | 2021-06-24 | Code |
| 27 | ViT-L | 191.2 | No | DeiT III: Revenge of the ViT | 2022-04-14 | Code |
| 28 | XCiT-M24 | 188 | No | XCiT: Cross-Covariance Image Transformers | 2021-06-17 | Code |
| 29 | ConvNeXt-XL (ImageNet-22k) | 179 | No | A ConvNet for the 2020s | 2022-01-10 | Code |
| 30 | ResNeXt-101 32x32d | 174 | No | Exploring the Limits of Weakly Supervised Pretra... | 2018-05-02 | Code |
| 31 | CAIT-M-36 | 173.3 | No | Going deeper with Image Transformers | 2021-03-31 | Code |
| 32 | InternImage-XL | 163 | No | InternImage: Exploring Large-Scale Vision Founda... | 2022-11-10 | Code |
| 33 | FasterViT-6 | 142 | No | FasterViT: Fast Vision Transformers with Hierarc... | 2023-06-09 | Code |
| 34 | MViTv2-L (384 res, ImageNet-21k pretrain) | 140.7 | No | MViTv2: Improved Multiscale Vision Transformers ... | 2021-12-02 | Code |
| 35 | MViTv2-L (384 res) | 140.2 | No | MViTv2: Improved Multiscale Vision Transformers ... | 2021-12-02 | Code |
| 36 | RepLKNet-XL | 128.7 | No | Scaling Up Your Kernels to 31x31: Revisiting Lar... | 2022-03-13 | Code |
| 37 | MViTv2-H (mageNet-21k pretrain) | 120.6 | No | MViTv2: Improved Multiscale Vision Transformers ... | 2021-12-02 | Code |
| 38 | CAIT-M-24 | 116.1 | No | Going deeper with Image Transformers | 2021-03-31 | Code |
| 39 | NFNet-F3 | 114.76 | No | High-Performance Large-Scale Image Recognition W... | 2021-02-11 | Code |
| 40 | VAN-B6 (22K, 384res) | 114.3 | No | Visual Attention Network | 2022-02-20 | Code |
| 41 | CoAtNet-3 @384 | 114 | No | CoAtNet: Marrying Convolution and Attention for ... | 2021-06-09 | Code |
| 42 | FasterViT-5 | 113 | No | FasterViT: Fast Vision Transformers with Hierarc... | 2023-06-09 | Code |
| 43 | InternImage-L | 108 | No | InternImage: Exploring Large-Scale Vision Founda... | 2022-11-10 | Code |
| 44 | XCiT-S24 | 106 | No | XCiT: Cross-Covariance Image Transformers | 2021-06-17 | Code |
| 45 | Swin-L | 103.9 | No | Swin Transformer: Hierarchical Vision Transforme... | 2021-03-25 | Code |
| 46 | DaViT-L (ImageNet-22k) | 103 | No | DaViT: Dual Attention Vision Transformers | 2022-04-07 | Code |
| 47 | MogaNet-XL (384res) | 102 | No | MogaNet: Multi-order Gated Aggregation Network | 2022-11-07 | Code |
| 48 | HorNet-L (GF) | 101.8 | No | HorNet: Efficient High-Order Spatial Interaction... | 2022-07-28 | Code |
| 49 | DiNAT_s-Large (384res; Pretrained on IN22K@224) | 101.5 | No | Dilated Neighborhood Attention Transformer | 2022-09-29 | Code |
| 50 | ConvNeXt-L (384 res) | 101 | No | A ConvNet for the 2020s | 2022-01-10 | Code |
| 51 | Mini-Swin-B@384 | 98.8 | No | MiniViT: Compressing Vision Transformers with We... | 2022-04-14 | Code |
| 52 | CSWin-L (384 res,ImageNet-22k pretrain) | 96.8 | No | CSWin Transformer: A General Vision Transformer ... | 2021-07-01 | Code |
| 53 | EfficientNetV2-XL (21k) | 94 | Yes | EfficientNetV2: Smaller Models and Faster Training | 2021-04-01 | Code |
| 54 | DiNAT-Large (11x11ks; 384res; Pretrained on IN22K@224) | 92.4 | No | Dilated Neighborhood Attention Transformer | 2022-09-29 | Code |
| 55 | DiNAT-Large (384x384; Pretrained on ImageNet-22K @ 224x224) | 89.7 | No | Dilated Neighborhood Attention Transformer | 2022-09-29 | Code |
| 56 | FixEfficientNet-B7 | 82 | No | Fixing the train-test resolution discrepancy: Fi... | 2020-03-18 | Code |
| 57 | CAFormer-B36 (384 res, 21K) | 72.2 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 58 | CAFormer-B36 (384 res) | 72.2 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 59 | ResNeXt-101 32×16d | 72 | No | Exploring the Limits of Weakly Supervised Pretra... | 2018-05-02 | Code |
| 60 | VOLO-D3 | 67.9 | No | VOLO: Vision Outlooker for Visual Recognition | 2021-06-24 | Code |
| 61 | MIRL (ViT-B-48) | 67 | No | Masked Image Residual Learning for Scaling Deepe... | 2023-09-25 | Code |
| 62 | ConvFormer-B36 (384 res, 21K) | 66.5 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 63 | ConvFormer-B36 (384 res) | 66.5 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 64 | CAIT-S-48 | 63.8 | No | Going deeper with Image Transformers | 2021-03-31 | Code |
| 65 | NFNet-F2 | 62.59 | No | High-Performance Large-Scale Image Recognition W... | 2021-02-11 | Code |
| 66 | SE-ResNeXt-101, 64x4d, S=2(416px) | 61.1 | No | Towards Better Accuracy-efficiency Trade-offs: D... | 2020-11-30 | Code |
| 67 | CLCNet (S:ViT+D:VOLO-D3) (retrain) | 57.46 | No | CLCNet: Rethinking of Ensemble Modeling with Cla... | 2022-05-19 | Code |
| 68 | TransNeXt-Base (IN-1K supervised, 384) | 56.3 | No | TransNeXt: Robust Foveal Visual Perception for V... | 2023-11-28 | Code |
| 69 | XCiT-S12 | 55.6 | No | XCiT: Cross-Covariance Image Transformers | 2021-06-17 | Code |
| 70 | ResNet-RS-270 (256 image res) | 54 | No | Revisiting ResNets: Improved Training and Scalin... | 2021-03-13 | Code |
| 71 | EfficientNetV2-L (21k) | 53 | No | EfficientNetV2: Smaller Models and Faster Training | 2021-04-01 | Code |
| 72 | EfficientNetV2-L | 53 | No | EfficientNetV2: Smaller Models and Faster Training | 2021-04-01 | Code |
| 73 | CLCNet (S:ViT+D:EffNet-B7) (retrain) | 51.93 | No | CLCNet: Rethinking of Ensemble Modeling with Cla... | 2022-05-19 | Code |
| 74 | UniNet-B6 | 51 | No | UniNet: Unified Architecture Search with Convolu... | 2022-07-12 | Code |
| 75 | Sequencer2D-L↑392 | 50.7 | No | Sequencer: Deep LSTM for Image Classification | 2022-05-04 | Code |
| 76 | VAN-B5 (22K, 384res) | 50.6 | No | Visual Attention Network | 2022-02-20 | Code |
| 77 | PNASNet-5 | 50 | No | Progressive Neural Architecture Search | 2017-12-02 | Code |
| 78 | DAT-B (384 res, IN-1K only) | 49.8 | No | Vision Transformer with Deformable Attention | 2022-01-03 | Code |
| 79 | DAT-B++ (384x384) | 49.7 | No | DAT++: Spatially Dynamic Vision Transformer with... | 2023-09-04 | Code |
| 80 | CAIT-S-36 | 48 | No | Going deeper with Image Transformers | 2021-03-31 | Code |
| 81 | CLCNet (S:D1+D:D5) | 47.43 | No | CLCNet: Rethinking of Ensemble Modeling with Cla... | 2022-05-19 | Code |
| 82 | Swin-B | 47 | No | Swin Transformer: Hierarchical Vision Transforme... | 2021-03-25 | Code |
| 83 | Conformer-B | 46.6 | No | Conformer: Local Features Coupling Global Repres... | 2021-05-09 | Code |
| 84 | DaViT-B (ImageNet-22k) | 46.4 | No | DaViT: Dual Attention Vision Transformers | 2022-04-07 | Code |
| 85 | CLCNet (S:ConvNeXt-L+D:EffNet-B7) (retrain) | 45.43 | No | CLCNet: Rethinking of Ensemble Modeling with Cla... | 2022-05-19 | Code |
| 86 | MaxViT-L (224res) | 43.9 | No | MaxViT: Multi-Axis Vision Transformer | 2022-04-04 | Code |
| 87 | SReT-S (512 res, ImageNet-1K only) | 42.8 | No | Sliced Recursive Transformer | 2021-11-09 | Code |
| 88 | CAFormer-M36 (384 res, 21K) | 42 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 89 | CAFormer-M36 (384 res) | 42 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 90 | LITv2-B|384 | 39.7 | No | Fast Vision Transformers with HiLo Attention | 2022-05-26 | Code |
| 91 | UniFormer-L (384 res) | 39.2 | No | UniFormer: Unifying Convolution and Self-attenti... | 2022-01-24 | Code |
| 92 | VAN-B6 (22K) | 38.9 | No | Visual Attention Network | 2022-02-20 | Code |
| 93 | SE-ResNeXt-101, 64x4d, S=2(320px) | 38.2 | No | Towards Better Accuracy-efficiency Trade-offs: D... | 2020-11-30 | Code |
| 94 | RevBiFPN-S6 | 38.1 | No | RevBiFPN: The Fully Reversible Bidirectional Fea... | 2022-06-28 | Code |
| 95 | ConvFormer-M36 (384 res, 21K) | 37.7 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 96 | ConvFormer-M36 (384 res) | 37.7 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 97 | NoisyStudent (EfficientNet-B7) | 37 | No | Self-training with Noisy Student improves ImageN... | 2019-11-11 | Code |
| 98 | EfficientNet-B7 | 37 | No | EfficientNet: Rethinking Model Scaling for Convo... | 2019-05-28 | Code |
| 99 | FasterViT-4 | 36.6 | No | FasterViT: Fast Vision Transformers with Hierarc... | 2023-06-09 | Code |
| 100 | ActiveMLP-L | 36.4 | No | Active Token Mixer | 2022-03-11 | Code |
| 101 | VAN-B4 (22K, 384res) | 35.9 | No | Visual Attention Network | 2022-02-20 | Code |
| 102 | NFNet-F1 | 35.54 | No | High-Performance Large-Scale Image Recognition W... | 2021-02-11 | Code |
| 103 | DeiT-B with iRPE-K | 35.368 | No | Rethinking and Improving Relative Position Encod... | 2021-07-29 | Code |
| 104 | MambaVision-L | 34.9 | No | MambaVision: A Hybrid Mamba-Transformer Vision B... | 2024-07-10 | Code |
| 105 | RDNet-L (384 res) | 34.7 | No | DenseNets Reloaded: Paradigm Shift Beyond ResNet... | 2024-03-28 | Code |
| 106 | RDNet-L | 34.7 | No | DenseNets Reloaded: Paradigm Shift Beyond ResNet... | 2024-03-28 | Code |
| 107 | CoAtNet-3 | 34.7 | No | CoAtNet: Marrying Convolution and Attention for ... | 2021-06-09 | Code |
| 108 | DiNAT_s-Large (224x224; Pretrained on ImageNet-22K @ 224x224) | 34.5 | No | Dilated Neighborhood Attention Transformer | 2022-09-29 | Code |
| 109 | T2T-ViT-14|384 | 34.2 | No | Tokens-to-Token ViT: Training Vision Transformer... | 2021-01-28 | Code |
| 110 | MViT-B-24 | 32.7 | No | Multiscale Vision Transformers | 2021-04-22 | Code |
| 111 | CAIT-S-24 | 32.2 | No | Going deeper with Image Transformers | 2021-03-31 | Code |
| 112 | TransNeXt-Small (IN-1K supervised, 384) | 32.1 | No | TransNeXt: Robust Foveal Visual Perception for V... | 2023-11-28 | Code |
| 113 | Next-ViT-L @384 | 32 | No | Next-ViT: Next Generation Vision Transformer for... | 2022-07-12 | Code |
| 114 | VVT-L (384 res) | 31.8 | No | Vicinity Vision Transformer | 2022-06-21 | Code |
| 115 | gMLP-B | 31.6 | No | Pay Attention to MLPs | 2021-05-17 | Code |
| 116 | ResNeXt-101 64x4 | 31.5 | No | Aggregated Residual Transformations for Deep Neu... | 2016-11-16 | Code |
| 117 | Harm-SE-RNX-101 64x4d (320x320, Mean-Max Pooling) | 31.4 | No | Harmonic Convolutional Networks based on Discret... | 2020-01-18 | Code |
| 118 | TinySaver(ConvNeXtV2_h, 0.01 Acc drop) | 31.17 | No | Tiny Models are the Computational Saver for Larg... | 2024-03-26 | Code |
| 119 | T2T-ViTt-24 | 30 | No | Tokens-to-Token ViT: Training Vision Transformer... | 2021-01-28 | Code |
| 120 | ConViT-B+ | 30 | No | ConViT: Improving Vision Transformers with Soft ... | 2021-03-19 | Code |
| 121 | CAIT-XS-36 | 28.8 | No | Going deeper with Image Transformers | 2021-03-31 | Code |
| 122 | ViTAE-B-Stage | 27.6 | No | ViTAE: Vision Transformer Advanced by Exploring ... | 2021-06-07 | Code |
| 123 | T2T-ViT-24 | 27.6 | No | Tokens-to-Token ViT: Training Vision Transformer... | 2021-01-28 | Code |
| 124 | TinyViT-21M-512-distill (512 res, 21k) | 27 | No | TinyViT: Fast Pretraining Distillation for Small... | 2022-07-21 | Code |
| 125 | SE-CoTNetD-152 | 26.5 | No | Contextual Transformer Networks for Visual Recog... | 2021-07-26 | Code |
| 126 | CAFormer-S36 (384 res, 21K) | 26 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 127 | CAFormer-S36 (384 res) | 26 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 128 | CvT-21 (384 res, ImageNet-22k pretrain) | 25 | No | CvT: Introducing Convolutions to Vision Transfor... | 2021-03-29 | Code |
| 129 | CvT-21 (384 res) | 24.9 | No | CvT: Introducing Convolutions to Vision Transfor... | 2021-03-29 | Code |
| 130 | ResMLP-B24 + STD | 24.1 | No | - | - | Code |
| 131 | EfficientNetV2-M (21k) | 24 | No | EfficientNetV2: Smaller Models and Faster Training | 2021-04-01 | Code |
| 132 | NASNET-A(6) | 23.8 | No | Learning Transferable Architectures for Scalable... | 2017-07-21 | Code |
| 133 | MaxViT-B (224res) | 23.4 | No | MaxViT: Multi-Axis Vision Transformer | 2022-04-04 | Code |
| 134 | CAFormer-B36 (224 res, 21K) | 23.2 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 135 | CAFormer-B36 (224 res) | 23.2 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 136 | UniNet-B5 | 23.2 | No | UniNet: Unified Architecture Search with Convolu... | 2021-10-08 | - |
| 137 | MetaFormer PoolFormer-M48 | 23.2 | No | MetaFormer Is Actually What You Need for Vision | 2021-11-22 | Code |
| 138 | ConvFormer-B36 (224 res, 21K) | 22.6 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 139 | ConvFormer-B36 (224 res) | 22.6 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 140 | ConvFormer-S36 (384 res, 21K) | 22.4 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 141 | ConvFormer-S36 (384 res) | 22.4 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 142 | Oct-ResNet-152 (SE) | 22.2 | No | Drop an Octave: Reducing Spatial Redundancy in C... | 2019-04-10 | Code |
| 143 | RevBiFPN-S5 | 21.8 | No | RevBiFPN: The Fully Reversible Bidirectional Fea... | 2022-06-28 | Code |
| 144 | UniNet-B5 | 20.4 | No | UniNet: Unified Architecture Search with Convolu... | 2022-07-12 | Code |
| 145 | EfficientViT-L2 (r384) | 20 | No | EfficientViT: Multi-Scale Linear Attention for H... | 2022-05-29 | Code |
| 146 | T2T-ViTt-19 | 19.6 | No | Tokens-to-Token ViT: Training Vision Transformer... | 2021-01-28 | Code |
| 147 | TinySaver(ConvNeXtV2_h, 0.5 Acc drop) | 19.41 | No | Tiny Models are the Computational Saver for Larg... | 2024-03-26 | Code |
| 148 | CAIT-XS-24 | 19.3 | No | Going deeper with Image Transformers | 2021-03-31 | Code |
| 149 | BoTNet T5 | 19.3 | No | Bottleneck Transformers for Visual Recognition | 2021-01-27 | Code |
| 150 | EfficientNet-B6 | 19 | No | EfficientNet: Rethinking Model Scaling for Convo... | 2019-05-28 | Code |
| 151 | MIRL(ViT-S-54) | 18.8 | No | Masked Image Residual Learning for Scaling Deepe... | 2023-09-25 | Code |
| 152 | ResNeXt-101, 64x4d, S=2(224px) | 18.8 | No | Towards Better Accuracy-efficiency Trade-offs: D... | 2020-11-30 | Code |
| 153 | CLCNet (S:B4+D:B7) | 18.58 | No | CLCNet: Rethinking of Ensemble Modeling with Cla... | 2022-05-19 | Code |
| 154 | SReT-S (384 res, ImageNet-1K only) | 18.5 | No | Sliced Recursive Transformer | 2021-11-09 | Code |
| 155 | RepVGG-B2 | 18.4 | No | RepVGG: Making VGG-style ConvNets Great Again | 2021-01-11 | Code |
| 156 | FasterViT-3 | 18.2 | No | FasterViT: Fast Vision Transformers with Hierarc... | 2023-06-09 | Code |
| 157 | Transformer local-attention (NesT-B) | 17.9 | No | Nested Hierarchical Transformer: Towards Accurat... | 2021-05-26 | Code |
| 158 | RVT-B* | 17.7 | No | Towards Robust Vision Transformer | 2021-05-17 | Code |
| 159 | VAN-B5 (22K) | 17.2 | No | Visual Attention Network | 2022-02-20 | Code |
| 160 | KAT-B* | 17.06 | No | Kolmogorov-Arnold Transformer | 2024-09-16 | Code |
| 161 | ConViT-B | 17 | No | ConViT: Improving Vision Transformers with Soft ... | 2021-03-19 | Code |
| 162 | GLiT-Bases | 17 | No | GLiT: Neural Architecture Search for Global and ... | 2021-07-07 | Code |
| 163 | T2T-ViT-19 | 17 | No | Tokens-to-Token ViT: Training Vision Transformer... | 2021-01-28 | Code |
| 164 | DeiT-B | 16.87 | No | Kolmogorov-Arnold Transformer | 2024-09-16 | Code |
| 165 | ViT-B/16 | 16.87 | No | Kolmogorov-Arnold Transformer | 2024-09-16 | Code |
| 166 | Pyramid ViG-B | 16.8 | No | Vision GNN: An Image is Worth Graph of Nodes | 2022-06-01 | Code |
| 167 | DAT-B++ (224x224) | 16.6 | No | DAT++: Spatially Dynamic Vision Transformer with... | 2023-09-04 | Code |
| 168 | Sequencer2D-L | 16.6 | No | Sequencer: Deep LSTM for Image Classification | 2022-05-04 | Code |
| 169 | MixMIM-B | 16.3 | No | MixMAE: Mixed and Masked Autoencoder for Efficie... | 2022-05-26 | Code |
| 170 | CvT-13 (384 res) | 16.3 | No | CvT: Introducing Convolutions to Vision Transfor... | 2021-03-29 | Code |
| 171 | InternImage-B | 16 | No | InternImage: Exploring Large-Scale Vision Founda... | 2022-11-10 | Code |
| 172 | LV-ViT-M | 16 | No | All Tokens Matter: Token Labeling for Training B... | 2021-04-22 | Code |
| 173 | MogaNet-L | 15.9 | No | MogaNet: Multi-order Gated Aggregation Network | 2022-11-07 | Code |
| 174 | Assemble-ResNet152 | 15.8 | No | Compounding the Performance Improvements of Asse... | 2020-01-17 | Code |
| 175 | BossNet-T1 | 15.8 | No | BossNAS: Exploring Hybrid CNN-transformers with ... | 2021-03-23 | Code |
| 176 | CoAtNet-2 | 15.7 | No | CoAtNet: Marrying Convolution and Attention for ... | 2021-06-09 | Code |
| 177 | DaViT-B | 15.5 | No | DaViT: Dual Attention Vision Transformers | 2022-04-07 | Code |
| 178 | ViT-S @384 (DeiT III) | 15.5 | No | DeiT III: Revenge of the ViT | 2022-04-14 | Code |
| 179 | RDNet-B | 15.4 | No | DenseNets Reloaded: Paradigm Shift Beyond ResNet... | 2024-03-28 | Code |
| 180 | DeepMAD-89M | 15.4 | No | DeepMAD: Mathematical Architecture Design for De... | 2023-03-05 | Code |
| 181 | Shift-B | 15.2 | No | When Shift Operation Meets Vision Transformer: A... | 2022-01-26 | Code |
| 182 | Twins-SVT-L | 15.1 | No | Twins: Revisiting the Design of Spatial Attentio... | 2021-04-28 | Code |
| 183 | MambaVision-B | 15 | No | MambaVision: A Hybrid Mamba-Transformer Vision B... | 2024-07-10 | Code |
| 184 | Wave-ViT-L | 14.8 | No | Wave-ViT: Unifying Wavelet and Transformers for ... | 2022-07-11 | Code |
| 185 | GC ViT-B | 14.8 | No | Global Context Vision Transformers | 2022-06-20 | Code |
| 186 | CAIT-XXS-36 | 14.3 | No | Going deeper with Image Transformers | 2021-03-31 | Code |
| 187 | ZenNAS (0.8ms) | 13.9 | No | Zen-NAS: A Zero-Shot NAS for High-Performance De... | 2021-02-01 | Code |
| 188 | TinyViT-21M-384-distill (384 res, 21k) | 13.8 | No | TinyViT: Fast Pretraining Distillation for Small... | 2022-07-21 | Code |
| 189 | DiNAT-Base | 13.7 | No | Dilated Neighborhood Attention Transformer | 2022-09-29 | Code |
| 190 | NAT-Base | 13.7 | No | Neighborhood Attention Transformer | 2022-04-14 | Code |
| 191 | HRFormer-B | 13.7 | No | HRFormer: High-Resolution Transformer for Dense ... | 2021-10-18 | Code |
| 192 | CAFormer-S18 (384 res, 21K) | 13.4 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 193 | CAFormer-S18 (384 res) | 13.4 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 194 | ViL-Base-D | 13.4 | No | Multi-Scale Vision Longformer: A New Vision Tran... | 2021-03-29 | Code |
| 195 | CAFormer-M36 (224 res, 21K) | 13.2 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 196 | CAFormer-M36 (224 res) | 13.2 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 197 | LITv2-B | 13.2 | No | Fast Vision Transformers with HiLo Attention | 2022-05-26 | Code |
| 198 | GTP-DeiT-B/P8 | 13.1 | No | GTP-ViT: Efficient Vision Transformers via Graph... | 2023-11-06 | Code |
| 199 | CeiT-S (384 finetune res) | 12.9 | No | Incorporating Convolution Designs into Visual Tr... | 2021-03-22 | Code |
| 200 | ConvFormer-M36 (224 res, 21K) | 12.8 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 201 | ConvFormer-M36 (224 res) | 12.8 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 202 | UniFormer-L | 12.6 | No | UniFormer: Unifying Convolution and Self-attenti... | 2022-01-24 | Code |
| 203 | PiT-B | 12.5 | No | Rethinking Spatial Dimensions of Vision Transfor... | 2021-03-30 | Code |
| 204 | NFNet-F0 | 12.38 | No | High-Performance Large-Scale Image Recognition W... | 2021-02-11 | Code |
| 205 | CycleMLP-B5 | 12.3 | No | CycleMLP: A MLP-like Architecture for Dense Pred... | 2021-07-21 | Code |
| 206 | VAN-B4 (22K) | 12.2 | No | Visual Attention Network | 2022-02-20 | Code |
| 207 | ViTAE-S-Stage | 12 | No | ViTAE: Vision Transformer Advanced by Exploring ... | 2021-06-07 | Code |
| 208 | PVTv2-B4 | 11.8 | No | PVT v2: Improved Baselines with Pyramid Vision T... | 2021-06-25 | Code |
| 209 | MaxViT-S (224res) | 11.7 | No | MaxViT: Multi-Axis Vision Transformer | 2022-04-04 | Code |
| 210 | ConvFormer-S18 (384 res, 21K) | 11.6 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 211 | ConvFormer-S18 (384 res) | 11.6 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 212 | ResNet-152 | 11.3 | No | Deep Residual Learning for Image Recognition | 2015-12-10 | Code |
| 213 | RepVGG-B2g4 | 11.3 | No | RepVGG: Making VGG-style ConvNets Great Again | 2021-01-11 | Code |
| 214 | ScaleNet-152 | 11.2 | No | Data-Driven Neuron Allocation for Scale Aggregat... | 2019-04-20 | Code |
| 215 | Sequencer2D-M | 11.1 | No | Sequencer: Deep LSTM for Image Classification | 2022-05-04 | Code |
| 216 | CCT-14/7x2 | 11.06 | No | Escaping the Big Data Paradigm with Compact Tran... | 2021-04-12 | Code |
| 217 | EfficientViT-L2 (r288) | 11 | No | EfficientViT: Multi-Scale Linear Attention for H... | 2022-05-29 | Code |
| 218 | AutoFormer-base | 11 | No | AutoFormer: Searching Transformers for Visual Re... | 2021-07-01 | Code |
| 219 | BoTNet T4 | 10.9 | No | Bottleneck Transformers for Visual Recognition | 2021-01-27 | Code |
| 220 | ECA-Net (ResNet-152) | 10.83 | No | ECA-Net: Efficient Channel Attention for Deep Co... | 2019-10-08 | Code |
| 221 | VVT-L (224 res) | 10.8 | No | Vicinity Vision Transformer | 2022-06-21 | Code |
| 222 | RevBiFPN-S4 | 10.6 | No | RevBiFPN: The Fully Reversible Bidirectional Fea... | 2022-06-28 | Code |
| 223 | Transformer local-attention (NesT-S) | 10.4 | No | Nested Hierarchical Transformer: Towards Accurat... | 2021-05-26 | Code |
| 224 | TransNeXt-Small (IN-1K supervised, 224) | 10.3 | No | TransNeXt: Robust Foveal Visual Perception for V... | 2023-11-28 | Code |
| 225 | ConViT-S+ | 10 | No | ConViT: Improving Vision Transformers with Soft ... | 2021-03-19 | Code |
| 226 | MogaNet-B | 9.9 | No | MogaNet: Multi-order Gated Aggregation Network | 2022-11-07 | Code |
| 227 | UniNet-B4 | 9.9 | No | UniNet: Unified Architecture Search with Convolu... | 2021-10-08 | - |
| 228 | EfficientNet-B5 | 9.9 | No | EfficientNet: Rethinking Model Scaling for Convo... | 2019-05-28 | Code |
| 229 | DeiT-S with iRPE-QKV | 9.77 | No | Rethinking and Improving Relative Position Encod... | 2021-07-29 | Code |
| 230 | QnA-ViT-Base | 9.7 | No | Learned Queries for Efficient Local Attention | 2021-12-21 | Code |
| 231 | T2T-ViT-14 | 9.6 | No | Tokens-to-Token ViT: Training Vision Transformer... | 2021-01-28 | Code |
| 232 | CAIT-XXS-24 | 9.6 | No | Going deeper with Image Transformers | 2021-03-31 | Code |
| 233 | CrossViT-18+ | 9.5 | No | CrossViT: Cross-Attention Multi-Scale Vision Tra... | 2021-03-27 | Code |
| 234 | DeiT-S with iRPE-QK | 9.412 | No | Rethinking and Improving Relative Position Encod... | 2021-07-29 | Code |
| 235 | DAT-S++ | 9.4 | No | DAT++: Spatially Dynamic Vision Transformer with... | 2023-09-04 | Code |
| 236 | CentroidViT-S (arXiv, 2021-02) | 9.4 | No | Centroid Transformers: Learning to Abstract with... | 2021-02-17 | - |
| 237 | DeiT-S with iRPE-K | 9.318 | No | Rethinking and Improving Relative Position Encod... | 2021-07-29 | Code |
| 238 | SpineNet-143 | 9.1 | No | SpineNet: Learning Scale-Permuted Backbone for R... | 2019-12-10 | Code |
| 239 | DAT-S | 9 | No | Vision Transformer with Deformable Attention | 2022-01-03 | Code |
| 240 | CrossViT-18 | 9 | No | CrossViT: Cross-Attention Multi-Scale Vision Tra... | 2021-03-27 | Code |
| 241 | Pyramid ViG-M | 8.9 | No | Vision GNN: An Image is Worth Graph of Nodes | 2022-06-01 | Code |
| 242 | EfficientNetV2-S (21k) | 8.8 | No | EfficientNetV2: Smaller Models and Faster Training | 2021-04-01 | Code |
| 243 | FasterViT-2 | 8.7 | No | FasterViT: Fast Vision Transformers with Hierarc... | 2023-06-09 | Code |
| 244 | RDNet-S | 8.7 | No | DenseNets Reloaded: Paradigm Shift Beyond ResNet... | 2024-03-28 | Code |
| 245 | ViL-Medium-D | 8.7 | No | Multi-Scale Vision Longformer: A New Vision Tran... | 2021-03-29 | Code |
| 246 | GFNet-H-B | 8.6 | No | Global Filter Networks for Image Classification | 2021-07-01 | Code |
| 247 | GC ViT-S | 8.5 | No | Global Context Vision Transformers | 2022-06-20 | Code |
| 248 | SE-CoTNetD-101 | 8.5 | No | Contextual Transformer Networks for Visual Recog... | 2021-07-26 | Code |
| 249 | Shift-S | 8.5 | No | When Shift Operation Meets Vision Transformer: A... | 2022-01-26 | Code |
| 250 | SKNet-101 | 8.46 | No | Selective Kernel Networks | 2019-03-15 | Code |
| 251 | CoAtNet-1 | 8.4 | No | CoAtNet: Marrying Convolution and Attention for ... | 2021-06-09 | Code |
| 252 | SCARLET-A4 | 8.4 | No | SCARLET-NAS: Bridging the Gap between Stability ... | 2019-08-16 | Code |
| 253 | Sequencer2D-S | 8.4 | No | Sequencer: Deep LSTM for Image Classification | 2022-05-04 | Code |
| 254 | Next-ViT-B | 8.3 | No | Next-ViT: Next Generation Vision Transformer for... | 2022-07-12 | Code |
| 255 | Container Container | 8.1 | No | Container: Context Aggregation Network | 2021-06-02 | Code |
| 256 | CAFormer-S36 (224 res, 21K) | 8 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 257 | ELSA-VOLO-D1 | 8 | No | ELSA: Enhanced Local Self-Attention for Vision T... | 2021-12-23 | Code |
| 258 | CAFormer-S36 (224 res) | 8 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 259 | InternImage-S | 8 | No | InternImage: Exploring Large-Scale Vision Founda... | 2022-11-10 | Code |
| 260 | GTP-LV-ViT-M/P8 | 8 | No | GTP-ViT: Efficient Vision Transformers via Graph... | 2023-11-06 | Code |
| 261 | RegNetY-8.0GF | 8 | No | Designing Network Design Spaces | 2020-03-30 | Code |
| 262 | ResT-Large | 7.9 | No | ResT: An Efficient Transformer for Visual Recogn... | 2021-05-28 | Code |
| 263 | RandWire-WS | 7.9 | No | Exploring Randomly Wired Neural Networks for Ima... | 2019-04-02 | Code |
| 264 | SGE-ResNet101 | 7.858 | No | Spatial Group-wise Enhance: Improving Semantic F... | 2019-05-23 | Code |
| 265 | DiNAT-Small | 7.8 | No | Dilated Neighborhood Attention Transformer | 2022-09-29 | Code |
| 266 | NAT-Small | 7.8 | No | Neighborhood Attention Transformer | 2022-04-14 | Code |
| 267 | IPT-B | 7.8 | No | IncepFormer: Efficient Inception Transformer wit... | 2022-12-06 | Code |
| 268 | MViT-B-16 | 7.8 | No | Multiscale Vision Transformers | 2021-04-22 | Code |
| 269 | ConvFormer-S36 (224 res, 21K) | 7.6 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 270 | ConvFormer-S36 (224 res) | 7.6 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 271 | ResNet-101 | 7.6 | No | Deep Residual Learning for Image Recognition | 2015-12-10 | Code |
| 272 | AOGNet-40M-AN | 7.51 | No | Attentive Normalization | 2019-08-04 | Code |
| 273 | LITv2-M | 7.5 | No | Fast Vision Transformers with HiLo Attention | 2022-05-26 | Code |
| 274 | MambaVision-S | 7.5 | No | MambaVision: A Hybrid Mamba-Transformer Vision B... | 2024-07-10 | Code |
| 275 | ScaleNet-101 | 7.5 | No | Data-Driven Neuron Allocation for Scale Aggregat... | 2019-04-20 | Code |
| 276 | ECA-Net (ResNet-101) | 7.35 | No | ECA-Net: Efficient Channel Attention for Deep Co... | 2019-10-08 | Code |
| 277 | BoTNet T3 | 7.3 | No | Bottleneck Transformers for Visual Recognition | 2021-01-27 | Code |
| 278 | Wave-ViT-B | 7.2 | No | Wave-ViT: Unifying Wavelet and Transformers for ... | 2022-07-11 | Code |
| 279 | CvT-21 | 7.1 | No | CvT: Introducing Convolutions to Vision Transfor... | 2021-03-29 | Code |
| 280 | HCGNet-C | 7.1 | No | Gated Convolutional Networks with Hybrid Connect... | 2019-08-26 | Code |
| 281 | gSwin-S | 7 | No | gSwin: Gated MLP Vision Model with Hierarchical ... | 2022-08-24 | - |
| 282 | PVTv2-B3 | 6.9 | No | PVT v2: Improved Baselines with Pyramid Vision T... | 2021-06-25 | Code |
| 283 | ViTAE-13M | 6.8 | No | ViTAE: Vision Transformer Advanced by Exploring ... | 2021-06-07 | Code |
| 284 | RedNet-152 | 6.8 | No | Involution: Inverting the Inherence of Convoluti... | 2021-03-10 | Code |
| 285 | ViL-Base-W | 6.74 | No | Multi-Scale Vision Longformer: A New Vision Tran... | 2021-03-29 | Code |
| 286 | LV-ViT-S | 6.6 | No | All Tokens Matter: Token Labeling for Training B... | 2021-04-22 | Code |
| 287 | EfficientViT-B3 (r288) | 6.5 | No | EfficientViT: Multi-Scale Linear Attention for H... | 2022-05-29 | Code |
| 288 | CI2P-ViT | 6.442 | No | Compress image to patches for Vision Transformer | 2025-02-14 | Code |
| 289 | CrossViT-15+ | 6.1 | No | CrossViT: Cross-Attention Multi-Scale Vision Tra... | 2021-03-27 | Code |
| 290 | ResMLP-S24 | 6 | No | ResMLP: Feedforward networks for image classific... | 2021-05-07 | Code |
| 291 | Next-ViT-S | 5.8 | No | Next-ViT: Next Generation Vision Transformer for... | 2022-07-12 | Code |
| 292 | Transformer local-attention (NesT-T) | 5.8 | No | Nested Hierarchical Transformer: Towards Accurat... | 2021-05-26 | Code |
| 293 | CrossViT-15 | 5.8 | No | CrossViT: Cross-Attention Multi-Scale Vision Tra... | 2021-03-27 | Code |
| 294 | TransNeXt-Tiny (IN-1K supervised, 224) | 5.7 | No | TransNeXt: Robust Foveal Visual Perception for V... | 2023-11-28 | Code |
| 295 | MOAT-0 1K only | 5.7 | No | MOAT: Alternating Mobile Convolution and Attenti... | 2022-10-04 | Code |
| 296 | MaxViT-T (224res) | 5.6 | No | MaxViT: Multi-Axis Vision Transformer | 2022-04-04 | Code |
| 297 | ConViT-S | 5.4 | No | ConViT: Improving Vision Transformers with Soft ... | 2021-03-19 | Code |
| 298 | ResNeSt-50 | 5.39 | No | ResNeSt: Split-Attention Networks | 2020-04-19 | Code |
| 299 | EfficientViT-L1 (r224) | 5.3 | No | EfficientViT: Multi-Scale Linear Attention for H... | 2022-05-29 | Code |
| 300 | FasterViT-1 | 5.3 | No | FasterViT: Fast Vision Transformers with Hierarc... | 2023-06-09 | Code |
| 301 | MambaVision-T2 | 5.1 | No | MambaVision: A Hybrid Mamba-Transformer Vision B... | 2024-07-10 | Code |
| 302 | AutoFormer-small | 5.1 | No | AutoFormer: Searching Transformers for Visual Re... | 2021-07-01 | Code |
| 303 | MogaNet-S | 5 | No | MogaNet: Multi-order Gated Aggregation Network | 2022-11-07 | Code |
| 304 | RDNet-T | 5 | No | DenseNets Reloaded: Paradigm Shift Beyond ResNet... | 2024-03-28 | Code |
| 305 | VAN-B2 | 5 | No | Visual Attention Network | 2022-02-20 | Code |
| 306 | Visformer-S | 4.9 | No | Visformer: The Vision-friendly Transformer | 2021-04-26 | Code |
| 307 | ViL-Small | 4.86 | No | Multi-Scale Vision Longformer: A New Vision Tran... | 2021-03-29 | Code |
| 308 | ELSA-Swin-T | 4.8 | No | ELSA: Enhanced Local Self-Attention for Vision T... | 2021-12-23 | Code |
| 309 | GTP-LV-ViT-S/P8 | 4.8 | No | GTP-ViT: Efficient Vision Transformers via Graph... | 2023-11-06 | Code |
| 310 | LocalViT-PVT | 4.8 | No | LocalViT: Bringing Locality to Vision Transformers | 2021-04-12 | Code |
| 311 | Wave-ViT-S | 4.7 | No | Wave-ViT: Unifying Wavelet and Transformers for ... | 2022-07-11 | Code |
| 312 | GC ViT-T | 4.7 | No | Global Context Vision Transformers | 2022-06-20 | Code |
| 313 | IPT-S | 4.7 | No | IncepFormer: Efficient Inception Transformer wit... | 2022-12-06 | Code |
| 314 | MViTv2-T | 4.7 | No | MViTv2: Improved Multiscale Vision Transformers ... | 2021-12-02 | Code |
| 315 | RVT-S* | 4.7 | No | Towards Robust Vision Transformer | 2021-05-17 | Code |
| 316 | RedNet-101 | 4.7 | No | Involution: Inverting the Inherence of Convoluti... | 2021-03-10 | Code |
| 317 | ResNet-RS-50 (160 image res) | 4.6 | No | Revisiting ResNets: Improved Training and Scalin... | 2021-03-13 | Code |
| 318 | Pyramid ViG-S | 4.6 | No | Vision GNN: An Image is Worth Graph of Nodes | 2022-06-01 | Code |
| 319 | DAT-T | 4.6 | No | Vision Transformer with Deformable Attention | 2022-01-03 | Code |
| 320 | LocalViT-S | 4.6 | No | LocalViT: Bringing Locality to Vision Transformers | 2021-04-12 | Code |
| 321 | ViTAE-T-Stage | 4.6 | No | ViTAE: Vision Transformer Advanced by Exploring ... | 2021-06-07 | Code |
| 322 | ConvNeXt-T | 4.5 | No | A ConvNet for the 2020s | 2022-01-10 | Code |
| 323 | CeiT-S | 4.5 | No | Incorporating Convolution Designs into Visual Tr... | 2021-03-22 | Code |
| 324 | CvT-13 | 4.5 | No | CvT: Introducing Convolutions to Vision Transfor... | 2021-03-29 | Code |
| 325 | Swin-T | 4.5 | No | Swin Transformer: Hierarchical Vision Transforme... | 2021-03-25 | Code |
| 326 | QnA-ViT-Small | 4.4 | No | Learned Queries for Efficient Local Attention | 2021-12-21 | Code |
| 327 | MambaVision-T | 4.4 | No | MambaVision: A Hybrid Mamba-Transformer Vision B... | 2024-07-10 | Code |
| 328 | Shift-T | 4.4 | No | When Shift Operation Meets Vision Transformer: A... | 2022-01-26 | Code |
| 329 | GLiT-Smalls | 4.4 | No | GLiT: Neural Architecture Search for Global and ... | 2021-07-07 | Code |
| 330 | ResNeSt-50-fast | 4.34 | No | ResNeSt: Split-Attention Networks | 2020-04-19 | Code |
| 331 | TinyViT-21M-distill (21k) | 4.3 | No | TinyViT: Fast Pretraining Distillation for Small... | 2022-07-21 | Code |
| 332 | DAT-T++ | 4.3 | No | DAT++: Spatially Dynamic Vision Transformer with... | 2023-09-04 | Code |
| 333 | NAT-Tiny | 4.3 | No | Neighborhood Attention Transformer | 2022-04-14 | Code |
| 334 | TinyViT-21M | 4.3 | No | TinyViT: Fast Pretraining Distillation for Small... | 2022-07-21 | Code |
| 335 | DiNAT-Tiny | 4.3 | No | Dilated Neighborhood Attention Transformer | 2022-09-29 | Code |
| 336 | Mixer-S16 + STD | 4.3 | No | - | - | Code |
| 337 | EfficientNet-B4 | 4.2 | No | EfficientNet: Rethinking Model Scaling for Convo... | 2019-05-28 | Code |
| 338 | CoAtNet-0 | 4.2 | No | CoAtNet: Marrying Convolution and Attention for ... | 2021-06-09 | Code |
| 339 | SGE-ResNet50 | 4.127 | No | Spatial Group-wise Enhance: Improving Semantic F... | 2019-05-23 | Code |
| 340 | CAFormer-S18 (224 res, 21K) | 4.1 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 341 | CAFormer-S18 (224 res) | 4.1 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 342 | CvT-13-NAS | 4.1 | No | CvT: Introducing Convolutions to Vision Transfor... | 2021-03-29 | Code |
| 343 | SE-CoTNetD-50 | 4.1 | No | Contextual Transformer Networks for Visual Recog... | 2021-07-26 | Code |
| 344 | EfficientViT-B3 (r224) | 4 | No | EfficientViT: Multi-Scale Linear Attention for H... | 2022-05-29 | Code |
| 345 | CycleMLP-B2 + STD | 4 | No | - | - | Code |
| 346 | PVTv2-B2 | 4 | No | PVT v2: Improved Baselines with Pyramid Vision T... | 2021-06-25 | Code |
| 347 | ActiveMLP-T | 4 | No | Active Token Mixer | 2022-03-11 | Code |
| 348 | RegNetY-4.0GF | 4 | No | Designing Network Design Spaces | 2020-03-30 | Code |
| 349 | ViTAE-6M | 4 | No | ViTAE: Vision Transformer Advanced by Exploring ... | 2021-06-07 | Code |
| 350 | ConvFormer-S18 (224 res, 21K) | 3.9 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 351 | ConvFormer-S18 (224 res) | 3.9 | No | MetaFormer Baselines for Vision | 2022-10-24 | Code |
| 352 | ECA-Net (ResNet-50) | 3.86 | No | ECA-Net: Efficient Channel Attention for Deep Co... | 2019-10-08 | Code |
| 353 | ScaleNet-50 | 3.8 | No | Data-Driven Neuron Allocation for Scale Aggregat... | 2019-04-20 | Code |
| 354 | ResNet-50 | 3.8 | No | Deep Residual Learning for Image Recognition | 2015-12-10 | Code |
| 355 | LITv2-S | 3.7 | No | Fast Vision Transformers with HiLo Attention | 2022-05-26 | Code |
| 356 | DY-ResNet-18 | 3.7 | No | Dynamic Convolution: Attention over Convolution ... | 2019-12-07 | Code |
| 357 | UniFormer-S | 3.6 | No | UniFormer: Unifying Convolution and Self-attenti... | 2022-01-24 | Code |
| 358 | gSwin-T | 3.6 | No | gSwin: Gated MLP Vision Model with Hierarchical ... | 2022-08-24 | - |
| 359 | CeiT-T (384 finetune res) | 3.6 | No | Incorporating Convolution Designs into Visual Tr... | 2021-03-22 | Code |
| 360 | CAS-ViT-T | 3.597 | No | CAS-ViT: Convolutional Additive Self-attention V... | 2024-08-07 | Code |
| 361 | EdgeFormer-S | 3.48 | No | ParC-Net: Position Aware Circular Convolution wi... | 2022-03-08 | Code |
| 362 | ReXNet_3.0 | 3.4 | No | Rethinking Channel Dimensions for Efficient Mode... | 2020-07-02 | Code |
| 363 | GTP-DeiT-S/P8 | 3.4 | No | GTP-ViT: Efficient Vision Transformers via Graph... | 2023-11-06 | Code |
| 364 | RevBiFPN-S3 | 3.33 | No | RevBiFPN: The Fully Reversible Bidirectional Fea... | 2022-06-28 | Code |
| 365 | FasterViT-0 | 3.3 | No | FasterViT: Fast Vision Transformers with Hierarc... | 2023-06-09 | Code |
| 366 | Container-Light | 3.2 | No | Container: Context Aggregation Network | 2021-06-02 | Code |
| 367 | ResMLP-12 (distilled, class-MLP) | 3 | No | ResMLP: Feedforward networks for image classific... | 2021-05-07 | Code |
| 368 | ViTAE-T | 3 | No | ViTAE: Vision Transformer Advanced by Exploring ... | 2021-06-07 | Code |
| 369 | MobileOne-S4 | 2.978 | No | MobileOne: An Improved One millisecond Mobile Ba... | 2022-06-08 | Code |
| 370 | PiT-S | 2.9 | No | Rethinking Spatial Dimensions of Vision Transfor... | 2021-03-30 | Code |
| 371 | MobileOne-S4 (distill) | 2.9 | No | MobileOne: An Improved One millisecond Mobile Ba... | 2022-06-08 | Code |
| 372 | TransNeXt-Micro (IN-1K supervised, 224) | 2.7 | No | TransNeXt: Robust Foveal Visual Perception for V... | 2023-11-28 | Code |
| 373 | NAT-Mini | 2.7 | No | Neighborhood Attention Transformer | 2022-04-14 | Code |
| 374 | DiNAT-Mini | 2.7 | No | Dilated Neighborhood Attention Transformer | 2022-09-29 | Code |
| 375 | RedNet-50 | 2.7 | No | Involution: Inverting the Inherence of Convoluti... | 2021-03-10 | Code |
| 376 | GC ViT-XT | 2.6 | No | Global Context Vision Transformers | 2022-06-20 | Code |
| 377 | EdgeNeXt-S | 2.6 | No | EdgeNeXt: Efficiently Amalgamated CNN-Transforme... | 2022-06-21 | Code |
| 378 | LR-Net-26 | 2.6 | No | Local Relation Networks for Image Recognition | 2019-04-25 | Code |
| 379 | DeiT-Ti with iRPE-K | 2.568 | No | Rethinking and Improving Relative Position Encod... | 2021-07-29 | Code |
| 380 | QnA-ViT-Tiny | 2.5 | No | Learned Queries for Efficient Local Attention | 2021-12-21 | Code |
| 381 | VAN-B1 | 2.5 | No | Visual Attention Network | 2022-02-20 | Code |
| 382 | UniNet-B2 | 2.4 | No | UniNet: Unified Architecture Search with Convolu... | 2021-10-08 | - |
| 383 | HVT-S-1 | 2.4 | No | Scalable Vision Transformers with Hierarchical P... | 2021-03-19 | Code |
| 384 | LeViT-384 | 2.334 | No | LeViT: a Vision Transformer in ConvNet's Clothin... | 2021-04-02 | Code |
| 385 | IPT-T | 2.3 | No | IncepFormer: Efficient Inception Transformer wit... | 2022-12-06 | Code |
| 386 | gSwin-VT | 2.3 | No | gSwin: Gated MLP Vision Model with Hierarchical ... | 2022-08-24 | - |
| 387 | RedNet-38 | 2.2 | No | Involution: Inverting the Inherence of Convoluti... | 2021-03-10 | Code |
| 388 | Ghost-ResNet-50 (s=2) | 2.2 | No | GhostNet: More Features from Cheap Operations | 2019-11-27 | Code |
| 389 | FBNetV5-F-CLS | 2.1 | No | FBNetV5: Neural Architecture Search for Multiple... | 2021-11-19 | - |
| 390 | EfficientViT-B2 (r256) | 2.1 | No | EfficientViT: Multi-Scale Linear Attention for H... | 2022-05-29 | Code |
| 391 | GC ViT-XXT | 2.1 | No | Global Context Vision Transformers | 2022-06-20 | Code |
| 392 | PVTv2-B1 | 2.1 | No | PVT v2: Improved Baselines with Pyramid Vision T... | 2021-06-25 | Code |
| 393 | TinyViT-11M-distill (21k) | 2 | No | TinyViT: Fast Pretraining Distillation for Small... | 2022-07-21 | Code |
| 394 | CloFormer-S | 2 | No | Rethinking Local Perception in Lightweight Visio... | 2023-03-31 | Code |
| 395 | TinyViT-11M | 2 | No | TinyViT: Fast Pretraining Distillation for Small... | 2022-07-21 | Code |
| 396 | HCGNet-B | 2 | No | Gated Convolutional Networks with Hybrid Connect... | 2019-08-26 | Code |
| 397 | ConViT-Ti+ | 2 | No | ConViT: Improving Vision Transformers with Soft ... | 2021-03-19 | Code |
| 398 | ResT-Small | 1.9 | No | ResT: An Efficient Transformer for Visual Recogn... | 2021-05-28 | Code |
| 399 | MobileOne-S3 | 1.896 | No | MobileOne: An Improved One millisecond Mobile Ba... | 2022-06-08 | Code |
| 400 | CAS-ViT-M | 1.887 | No | CAS-ViT: Convolutional Additive Self-attention V... | 2024-08-07 | Code |
| 401 | NASViT (supernet) | 1.881 | No | - | - | Code |
| 402 | MobileViTv3-1.0 | 1.876 | No | MobileViTv3: Mobile-Friendly Vision Transformer ... | 2022-09-30 | Code |
| 403 | MobileViTv3-S | 1.841 | No | MobileViTv3: Mobile-Friendly Vision Transformer ... | 2022-09-30 | Code |
| 404 | DY-ResNet-10 | 1.82 | No | Dynamic Convolution: Attention over Convolution ... | 2019-12-07 | Code |
| 405 | HRFormer-T | 1.8 | No | HRFormer: High-Resolution Transformer for Dense ... | 2021-10-18 | Code |
| 406 | MobileViTv2-1.0 | 1.8 | No | Separable Self-attention for Mobile Vision Trans... | 2022-06-06 | Code |
| 407 | DVT (T2T-ViT-12) | 1.7 | No | Not All Images are Worth 16x16 Words: Dynamic Tr... | 2021-05-31 | Code |
| 408 | Pyramid ViG-Ti | 1.7 | No | Vision GNN: An Image is Worth Graph of Nodes | 2022-06-01 | Code |
| 409 | RedNet-26 | 1.7 | No | Involution: Inverting the Inherence of Convoluti... | 2021-03-10 | Code |
| 410 | FixEfficientNet-B0 | 1.6 | No | Fixing the train-test resolution discrepancy: Fi... | 2020-03-18 | Code |
| 411 | RegNetY-1.6GF | 1.6 | No | Designing Network Design Spaces | 2020-03-30 | Code |
| 412 | ReXNet_2.0 | 1.5 | No | Rethinking Channel Dimensions for Efficient Mode... | 2020-07-02 | Code |
| 413 | MogaNet-T (256res) | 1.44 | No | MogaNet: Multi-order Gated Aggregation Network | 2022-11-07 | Code |
| 414 | PiT-XS | 1.4 | No | Rethinking Spatial Dimensions of Vision Transfor... | 2021-03-30 | Code |
| 415 | GLiT-Tinys | 1.4 | No | GLiT: Neural Architecture Search for Global and ... | 2021-07-07 | Code |
| 416 | LocalViT-TNT | 1.4 | No | LocalViT: Bringing Locality to Vision Transformers | 2021-04-12 | Code |
| 417 | RevBiFPN-S2 | 1.37 | No | RevBiFPN: The Fully Reversible Bidirectional Fea... | 2022-06-28 | Code |
| 418 | TinyViT-5M-distill (21k) | 1.3 | No | TinyViT: Fast Pretraining Distillation for Small... | 2022-07-21 | Code |
| 419 | RVT-Ti* | 1.3 | No | Towards Robust Vision Transformer | 2021-05-17 | Code |
| 420 | TinyViT-5M | 1.3 | No | TinyViT: Fast Pretraining Distillation for Small... | 2022-07-21 | Code |
| 421 | Visformer-Ti | 1.3 | No | Visformer: The Vision-friendly Transformer | 2021-04-26 | Code |
| 422 | ViL-Tiny-RPB | 1.3 | No | Multi-Scale Vision Longformer: A New Vision Tran... | 2021-03-29 | Code |
| 423 | LocalViT-T | 1.3 | No | LocalViT: Bringing Locality to Vision Transformers | 2021-04-12 | Code |
| 424 | AutoFormer-tiny | 1.3 | No | AutoFormer: Searching Transformers for Visual Re... | 2021-07-01 | Code |
| 425 | MobileOne-S2 | 1.299 | No | MobileOne: An Improved One millisecond Mobile Ba... | 2022-06-08 | Code |
| 426 | SReT-LT (Fast Knowledge Distillation) | 1.2 | No | A Fast Knowledge Distillation Framework for Visu... | 2021-12-02 | Code |
| 427 | CeiT-T | 1.2 | No | Incorporating Convolution Designs into Visual Tr... | 2021-03-22 | Code |
| 428 | Ghost-ResNet-50 (s=4) | 1.2 | No | GhostNet: More Features from Cheap Operations | 2019-11-27 | Code |
| 429 | LocalViT-T2T | 1.2 | No | LocalViT: Bringing Locality to Vision Transformers | 2021-04-12 | Code |
| 430 | MobileNet-224 (CGD) | 1.198 | No | Compact Global Descriptor for Neural Networks | 2019-07-23 | Code |
| 431 | MobileNetV2 (1.4) | 1.17 | No | MobileNetV2: Inverted Residuals and Linear Bottl... | 2018-01-13 | Code |
| 432 | MobileNet-224 ×1.25 | 1.138 | No | MobileNets: Efficient Convolutional Neural Netwo... | 2017-04-17 | Code |
| 433 | CloFormer-XS | 1.1 | No | Rethinking Local Perception in Lightweight Visio... | 2023-03-31 | Code |
| 434 | SReT-T | 1.1 | No | Sliced Recursive Transformer | 2021-11-09 | Code |
| 435 | LeViT-256 | 1.066 | No | LeViT: a Vision Transformer in ConvNet's Clothin... | 2021-04-02 | Code |
| 436 | MobileViTv3-0.75 | 1.064 | No | MobileViTv3: Mobile-Friendly Vision Transformer ... | 2022-09-30 | Code |
| 437 | MogaNet-XT (256res) | 1.04 | No | MogaNet: Multi-order Gated Aggregation Network | 2022-11-07 | Code |
| 438 | FBNetV5-C-CLS | 1 | No | FBNetV5: Neural Architecture Search for Multiple... | 2021-11-19 | - |
| 439 | EfficientNet-B2 | 1 | No | EfficientNet: Rethinking Model Scaling for Convo... | 2019-05-28 | Code |
| 440 | MobileViTv2-0.75 | 1 | No | Separable Self-attention for Mobile Vision Trans... | 2022-06-06 | Code |
| 441 | ConViT-Ti | 1 | No | ConViT: Improving Vision Transformers with Soft ... | 2021-03-19 | Code |
| 442 | UniNet-B1 | 0.99 | No | UniNet: Unified Architecture Search with Convolu... | 2021-10-08 | - |
| 443 | CAS-ViT-S | 0.932 | No | CAS-ViT: Convolutional Additive Self-attention V... | 2024-08-07 | Code |
| 444 | MobileViTv3-XS | 0.927 | No | MobileViTv3: Mobile-Friendly Vision Transformer ... | 2022-09-30 | Code |
| 445 | VAN-B0 | 0.9 | No | Visual Attention Network | 2022-02-20 | Code |
| 446 | ReXNet_1.5 | 0.86 | No | Rethinking Channel Dimensions for Efficient Mode... | 2020-07-02 | Code |
| 447 | EfficientNet-B0 (CondConv) | 0.826 | No | CondConv: Conditionally Parameterized Convolutio... | 2019-04-10 | Code |
| 448 | MobileOne-S1 | 0.825 | No | MobileOne: An Improved One millisecond Mobile Ba... | 2022-06-08 | Code |
| 449 | ZenNet-400M-SE | 0.82 | No | Zen-NAS: A Zero-Shot NAS for High-Performance De... | 2021-02-01 | Code |
| 450 | MnasNet-A3 | 0.806 | No | MnasNet: Platform-Aware Neural Architecture Sear... | 2018-07-31 | Code |
| 451 | RegNetY-800MF | 0.8 | No | Designing Network Design Spaces | 2020-03-30 | Code |
| 452 | FairNAS-A | 0.776 | No | FairNAS: Rethinking Evaluation Fairness of Weigh... | 2019-07-03 | Code |
| 453 | NASViT-A5 | 0.757 | No | - | - | Code |
| 454 | SCARLET-A | 0.73 | No | SCARLET-NAS: Bridging the Gap between Stability ... | 2019-08-16 | Code |
| 455 | FBNetV5 | 0.726 | No | FBNetV5: Neural Architecture Search for Multiple... | 2021-11-19 | - |
| 456 | AlphaNet-A6 | 0.709 | No | AlphaNet: Improved Training of Supernets with Al... | 2021-02-16 | Code |
| 457 | DVT (T2T-ViT-10) | 0.7 | No | Not All Images are Worth 16x16 Words: Dynamic Tr... | 2021-05-31 | Code |
| 458 | EfficientNet-B1 | 0.7 | No | EfficientNet: Rethinking Model Scaling for Convo... | 2019-05-28 | Code |
| 459 | MobileViT-XS | 0.7 | No | MobileViT: Light-weight, General-purpose, and Mo... | 2021-10-05 | Code |
| 460 | PiT-Ti | 0.7 | No | Rethinking Spatial Dimensions of Vision Transfor... | 2021-03-30 | Code |
| 461 | SReT-ExT | 0.7 | No | Sliced Recursive Transformer | 2021-11-09 | Code |
| 462 | FairNAS-B | 0.69 | No | FairNAS: Rethinking Evaluation Fairness of Weigh... | 2019-07-03 | Code |
| 463 | FBNetV5-A-CLS | 0.685 | No | FBNetV5: Neural Architecture Search for Multiple... | 2021-11-19 | - |
| 464 | MnasNet-A2 | 0.68 | No | MnasNet: Platform-Aware Neural Architecture Sear... | 2018-07-31 | Code |
| 465 | ReXNet_1.3 | 0.66 | No | Rethinking Channel Dimensions for Efficient Mode... | 2020-07-02 | Code |
| 466 | SCARLET-B | 0.658 | No | SCARLET-NAS: Bridging the Gap between Stability ... | 2019-08-16 | Code |
| 467 | FairNAS-C | 0.642 | No | FairNAS: Rethinking Evaluation Fairness of Weigh... | 2019-07-03 | Code |
| 468 | HVT-Ti-1 | 0.64 | No | Scalable Vision Transformers with Hierarchical P... | 2021-03-19 | Code |
| 469 | MUXNet-l | 0.636 | No | MUXConv: Information Multiplexing in Convolution... | 2020-03-31 | Code |
| 470 | LeViT-192 | 0.624 | No | LeViT: a Vision Transformer in ConvNet's Clothin... | 2021-04-02 | Code |
| 471 | MnasNet-A1 | 0.624 | No | MnasNet: Platform-Aware Neural Architecture Sear... | 2018-07-31 | Code |
| 472 | RevBiFPN-S1 | 0.62 | No | RevBiFPN: The Fully Reversible Bidirectional Fea... | 2022-06-28 | Code |
| 473 | MoGA-A | 0.608 | No | MoGA: Searching Beyond MobileNetV3 | 2019-08-04 | Code |
| 474 | ESPNetv2 | 0.602 | No | ESPNetv2: A Light-weight, Power Efficient, and G... | 2018-11-28 | Code |
| 475 | DVT (T2T-ViT-7) | 0.6 | No | Not All Images are Worth 16x16 Words: Dynamic Tr... | 2021-05-31 | Code |
| 476 | CloFormer-XXS | 0.6 | No | Rethinking Local Perception in Lightweight Visio... | 2023-03-31 | Code |
| 477 | RegNetY-600MF | 0.6 | No | Designing Network Design Spaces | 2020-03-30 | Code |
| 478 | MobileNetV2 | 0.6 | Yes | MobileNetV2: Inverted Residuals and Linear Bottl... | 2018-01-13 | Code |
| 479 | PVTv2-B0 | 0.6 | No | PVT v2: Improved Baselines with Pyramid Vision T... | 2021-06-25 | Code |
| 480 | ShuffleNet V2 | 0.597 | No | ShuffleNet V2: Practical Guidelines for Efficien... | 2018-07-30 | Code |
| 481 | NASViT-A4 | 0.591 | No | - | - | Code |
| 482 | TinyNet (GhostNet-A) | 0.591 | No | Model Rubik's Cube: Twisting Resolution, Depth a... | 2020-10-28 | Code |
| 483 | RandWire-WS (small) | 0.583 | No | Exploring Randomly Wired Neural Networks for Ima... | 2019-04-02 | Code |
| 484 | MixNet-L | 0.565 | No | MixConv: Mixed Depthwise Convolutional Kernels | 2019-07-22 | Code |
| 485 | UniNet-B0 | 0.56 | No | UniNet: Unified Architecture Search with Convolu... | 2021-10-08 | - |
| 486 | CAS-ViT-XS | 0.56 | No | CAS-ViT: Convolutional Additive Self-attention V... | 2024-08-07 | Code |
| 487 | SCARLET-C | 0.56 | No | SCARLET-NAS: Bridging the Gap between Stability ... | 2019-08-16 | Code |
| 488 | UniNet-B0 | 0.555 | No | UniNet: Unified Architecture Search with Convolu... | 2022-07-12 | Code |
| 489 | DiCENet | 0.553 | No | DiCENet: Dimension-wise Convolutions for Efficie... | 2019-06-08 | Code |
| 490 | NASViT-A3 | 0.528 | No | - | - | Code |
| 491 | EdgeNeXt-XXS | 0.522 | No | EdgeNeXt: Efficiently Amalgamated CNN-Transforme... | 2022-06-21 | Code |
| 492 | MobileViTv2-0.5 | 0.5 | No | Separable Self-attention for Mobile Vision Trans... | 2022-06-06 | Code |
| 493 | AlphaNet-A5 | 0.491 | No | AlphaNet: Improved Training of Supernets with Al... | 2021-02-16 | Code |
| 494 | MobileViTv3-0.5 | 0.481 | No | MobileViTv3: Mobile-Friendly Vision Transformer ... | 2022-09-30 | Code |
| 495 | AlphaNet-A4 | 0.444 | No | AlphaNet: Improved Training of Supernets with Al... | 2021-02-16 | Code |
| 496 | MobileNet V3-Large 1.0 | 0.438 | No | Searching for MobileNetV3 | 2019-05-06 | Code |
| 497 | MUXNet-m | 0.436 | No | MUXConv: Information Multiplexing in Convolution... | 2020-03-31 | Code |
| 498 | DY-MobileNetV2 ×0.75 | 0.435 | No | Dynamic Convolution: Attention over Convolution ... | 2019-12-07 | Code |
| 499 | AsymmNet-Large ×1.0 | 0.4338 | No | AsymmNet: Towards ultralight convolution neural ... | 2021-04-15 | Code |
| 500 | NASViT-A2 | 0.421 | No | - | - | Code |
| 501 | ReXNet_1.0 | 0.4 | No | Rethinking Channel Dimensions for Efficient Mode... | 2020-07-02 | Code |
| 502 | RegNetY-400MF | 0.4 | No | Designing Network Design Spaces | 2020-03-30 | Code |
| 503 | DGPPF-ResNet50 | 0.4 | No | - | - | Code |
| 504 | EfficientNet-B0 | 0.39 | No | EfficientNet: Rethinking Model Scaling for Convo... | 2019-05-28 | Code |
| 505 | LeViT-128 | 0.376 | No | LeViT: a Vision Transformer in ConvNet's Clothin... | 2021-04-02 | Code |
| 506 | FBNet-C | 0.375 | No | FBNet: Hardware-Aware Efficient ConvNet Design v... | 2018-12-09 | Code |
| 507 | GreedyNAS-A | 0.366 | No | GreedyNAS: Towards Fast One-Shot NAS with Greedy... | 2020-03-25 | - |
| 508 | SkipblockNet-L | 0.364 | No | Bias Loss for Mobile Neural Networks | 2021-07-23 | Code |
| 509 | MixNet-M | 0.36 | No | MixConv: Mixed Depthwise Convolutional Kernels | 2019-07-22 | Code |
| 510 | AlphaNet-A3 | 0.357 | No | AlphaNet: Improved Training of Supernets with Al... | 2021-02-16 | Code |
| 511 | ReXNet_0.9 | 0.35 | No | Rethinking Channel Dimensions for Efficient Mode... | 2020-07-02 | Code |
| 512 | TinyNet-A + RA | 0.339 | No | Model Rubik's Cube: Twisting Resolution, Depth a... | 2020-10-28 | Code |
| 513 | GreedyNAS-B | 0.324 | No | GreedyNAS: Towards Fast One-Shot NAS with Greedy... | 2020-03-25 | - |
| 514 | ECA-Net (MobileNetV2) | 0.32 | No | ECA-Net: Efficient Channel Attention for Deep Co... | 2019-10-08 | Code |
| 515 | AlphaNet-A2 | 0.317 | No | AlphaNet: Improved Training of Supernets with Al... | 2021-02-16 | Code |
| 516 | RevBiFPN-S0 | 0.31 | No | RevBiFPN: The Fully Reversible Bidirectional Fea... | 2022-06-28 | Code |
| 517 | NASViT-A1 | 0.309 | No | - | - | Code |
| 518 | MobileViTv3-XXS | 0.289 | No | MobileViTv3: Mobile-Friendly Vision Transformer ... | 2022-09-30 | Code |
| 519 | LeViT-128S | 0.288 | No | LeViT: a Vision Transformer in ConvNet's Clothin... | 2021-04-02 | Code |
| 520 | GreedyNAS-C | 0.284 | No | GreedyNAS: Towards Fast One-Shot NAS with Greedy... | 2020-03-25 | - |
| 521 | FBNetV5-AC-CLS | 0.28 | No | FBNetV5: Neural Architecture Search for Multiple... | 2021-11-19 | - |
| 522 | AlphaNet-A1 | 0.279 | No | AlphaNet: Improved Training of Supernets with Al... | 2021-02-16 | Code |
| 523 | MobileOne-S0 (distill) | 0.275 | No | MobileOne: An Improved One millisecond Mobile Ba... | 2022-06-08 | Code |
| 524 | MixNet-S | 0.256 | No | MixConv: Mixed Depthwise Convolutional Kernels | 2019-07-22 | Code |
| 525 | SkipblockNet-M | 0.246 | No | Bias Loss for Mobile Neural Networks | 2021-07-23 | Code |
| 526 | MUXNet-s | 0.234 | No | MUXConv: Information Multiplexing in Convolution... | 2020-03-31 | Code |
| 527 | GhostNet ×1.3 | 0.226 | No | GhostNet: More Features from Cheap Operations | 2019-11-27 | Code |
| 528 | FBNetV5-AR-CLS | 0.215 | No | FBNetV5: Neural Architecture Search for Multiple... | 2021-11-19 | - |
| 529 | CoE-Large + CondConv | 0.214 | No | Collaboration of Experts: Achieving 80% Top-1 Ac... | 2021-07-08 | - |
| 530 | NASViT-A0 | 0.208 | No | - | - | Code |
| 531 | AlphaNet-A0 | 0.203 | No | AlphaNet: Improved Training of Supernets with Al... | 2021-02-16 | Code |
| 532 | DY-MobileNetV2 ×0.5 | 0.203 | No | Dynamic Convolution: Attention over Convolution ... | 2019-12-07 | Code |
| 533 | DGPPF-ResNet18 | 0.2 | No | - | - | Code |
| 534 | BasisNet-MV3 | 0.198 | No | BasisNet: Two-stage Model Synthesis for Efficien... | 2021-05-07 | - |
| 535 | CoE-Large | 0.194 | No | Collaboration of Experts: Achieving 80% Top-1 Ac... | 2021-07-08 | - |
| 536 | GhostNet ×1.0 | 0.141 | No | GhostNet: More Features from Cheap Operations | 2019-11-27 | Code |
| 537 | DY-MobileNetV3-Small | 0.137 | No | Dynamic Convolution: Attention over Convolution ... | 2019-12-07 | Code |
| 538 | AsymmNet-Large ×0.5 | 0.1344 | No | AsymmNet: Towards ultralight convolution neural ... | 2021-04-15 | Code |
| 539 | MUXNet-xs | 0.132 | No | MUXConv: Information Multiplexing in Convolution... | 2020-03-31 | Code |
| 540 | DY-MobileNetV2 ×0.35 | 0.124 | No | Dynamic Convolution: Attention over Convolution ... | 2019-12-07 | Code |
| 541 | AsymmNet-Small ×1.0 | 0.1154 | No | AsymmNet: Towards ultralight convolution neural ... | 2021-04-15 | Code |
| 542 | CoE-Small + CondConv + PWLU | 0.1 | No | Collaboration of Experts: Achieving 80% Top-1 Ac... | 2021-07-08 | - |
| 543 | DGPPF-MobileNetV2 | 0.1 | No | - | - | Code |
| 544 | GhostNet ×0.5 | 0.042 | No | GhostNet: More Features from Cheap Operations | 2019-11-27 | Code |