Image Classification on CIFAR-10

Metric: Percentage correct (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Percentage correct▼	Extra Data	Paper	Date↕	Code
1	ViT-H/14	99.5	Yes	An Image is Worth 16x16 Words: Transformers for ...	2020-10-22	Code
2	DINOv2 (ViT-g/14, frozen model, linear eval)	99.5	Yes	DINOv2: Learning Robust Visual Features without ...	2023-04-14	Code
3	µ2Net (ViT-L/16)	99.49	Yes	An Evolutionary Approach to Dynamic Introduction...	2022-05-25	Code
4	ViT-L/16	99.42	Yes	An Image is Worth 16x16 Words: Transformers for ...	2020-10-22	Code
5	CaiT-M-36 U 224	99.4	Yes	Going deeper with Image Transformers	2021-03-31	Code
6	CvT-W24	99.39	Yes	CvT: Introducing Convolutions to Vision Transfor...	2021-03-29	Code
7	BiT-L (ResNet)	99.37	Yes	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
8	RDNet-L (224 res, IN-1K pretrained)	99.31	Yes	DenseNets Reloaded: Paradigm Shift Beyond ResNet...	2024-03-28	Code
9	RDNet-B (224 res, IN-1K pretrained)	99.31	Yes	DenseNets Reloaded: Paradigm Shift Beyond ResNet...	2024-03-28	Code
10	ViT-B (attn fine-tune)	99.3	Yes	Three things everyone should know about Vision T...	2022-03-18	Code
11	Heinsen Routing + BEiT-large 16 224	99.2	Yes	An Algorithm for Routing Vectors in Sequences	2022-11-20	Code
12	ViT-B/16 (PUGD)	99.13	Yes	Perturbated Gradients Updating within Unit Space...	2021-10-01	Code
13	Astroformer	99.12	Yes	Astroformer: More Data Might not be all you need...	2023-04-03	Code
14	DeiT-B	99.1	Yes	Training data-efficient image transformers & dis...	2020-12-23	Code
15	TNT-B	99.1	Yes	Transformer in Transformer	2021-02-27	Code
16	CeiT-S (384 finetune resolution)	99.1	Yes	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
17	EfficientNetV2-L	99.1	Yes	EfficientNetV2: Smaller Models and Faster Training	2021-04-01	Code
18	AutoFormer-S \| 384	99.1	Yes	AutoFormer: Searching Transformers for Visual Re...	2021-07-01	Code
19	VIT-L/16 (Spinal FC, Background)	99.05	No	Reduction of Class Activation Uncertainty with B...	2023-05-05	Code
20	LaNet	99.03	No	-	-	Code
21	GPIPE + transfer learning	99	Yes	GPipe: Efficient Training of Giant Neural Networ...	2018-11-16	Code
22	TResNet-XL	99	No	TResNet: High Performance GPU-Dedicated Architec...	2020-03-30	Code
23	CeiT-S	99	No	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
24	EfficientNetV2-M	99	No	EfficientNetV2: Smaller Models and Faster Training	2021-04-01	Code
25	GFNet-H-B	99	Yes	Global Filter Networks for Image Classification	2021-07-01	Code
26	BiT-M (ResNet)	98.91	No	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
27	EfficientNet-B7	98.9	No	EfficientNet: Rethinking Model Scaling for Convo...	2019-05-28	Code
28	RDNet-T (224 res, IN-1K pretrained)	98.88	No	DenseNets Reloaded: Paradigm Shift Beyond ResNet...	2024-03-28	Code
29	PyramidNet-272, S=4	98.71	No	Towards Better Accuracy-efficiency Trade-offs: D...	2020-11-30	Code
30	EfficientNetV2-S	98.7	No	EfficientNetV2: Smaller Models and Faster Training	2021-04-01	Code
31	ASF-former-S	98.7	No	Adaptive Split-Fusion Transformer	2022-04-26	Code
32	PyramidNet-272 (ASAM)	98.68	No	ASAM: Adaptive Sharpness-Aware Minimization for ...	2021-02-23	Code
33	PyramidNet + ShakeDrop + Fast AA + FMix	98.64	No	FMix: Enhancing Mixed Sample Data Augmentation	2020-02-27	Code
34	ViT-B/16- SAM	98.6	No	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
35	ConvMLP-M	98.6	Yes	ConvMLP: Hierarchical Convolutional MLPs for Vis...	2021-09-09	Code
36	ConvMLP-L	98.6	Yes	ConvMLP: Hierarchical Convolutional MLPs for Vis...	2021-09-09	Code
37	DVT (T2T-ViT-24)	98.53	No	Not All Images are Worth 16x16 Words: Dynamic Tr...	2021-05-31	Code
38	E2E-3M	98.52	No	Rethinking Recurrent Neural Networks and Other I...	2020-07-30	Code
39	CeiT-T	98.5	No	Incorporating Convolution Designs into Visual Tr...	2021-03-22	Code
40	NAT-M4	98.4	Yes	Neural Architecture Transfer	2020-05-12	Code
41	WRN-40-10, S=4	98.38	No	Towards Better Accuracy-efficiency Trade-offs: D...	2020-11-30	Code
42	WRN-28-10, S=4	98.32	No	Towards Better Accuracy-efficiency Trade-offs: D...	2020-11-30	Code
43	Shake-Shake 26 2x96d, S=4	98.31	No	Towards Better Accuracy-efficiency Trade-offs: D...	2020-11-30	Code
44	Dynamics 2	98.31	No	PSO-Convolutional Neural Networks with Heterogen...	2022-05-20	Code
45	PyramidNet+ShakeDrop (Fast AA)	98.3	No	Fast AutoAugment	2019-05-01	Code
46	ResNet50 (A1)	98.3	No	ResNet strikes back: An improved training proced...	2021-10-01	Code
47	NoisyDARTS-A-t	98.28	No	Noisy Differentiable Architecture Search	2020-05-07	Code
48	NAT-M3	98.2	Yes	Neural Architecture Transfer	2020-05-12	Code
49	LeViT-192	98.2	No	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
50	ResNet-152-SAM	98.2	No	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
51	ViT-S/16- SAM	98.2	No	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
52	Bamboo (ViT-B/16)	98.2	No	Bamboo: Building Mega-Scale Vision Dataset Conti...	2022-03-15	Code
53	DE ELBo (ViT-B/16)	98.2	No	Learning Hyperparameters via a Data-Emphasized V...	2025-02-03	Code
54	LeViT-256	98.1	Yes	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
55	PyramidNet + AA (AMP)	98.02	No	Regularizing Neural Networks via Adversarial Mod...	2020-10-10	Code
56	EnAET	98.01	No	EnAET: A Self-Trained framework for Semi-Supervi...	2019-11-21	Code
57	MUXNet-m	98	No	MUXConv: Information Multiplexing in Convolution...	2020-03-31	Code
58	LeViT-384	98	No	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
59	CCT-7/3x1*	98	No	Escaping the Big Data Paradigm with Compact Tran...	2021-04-12	Code
60	ConvMLP-S	98	Yes	ConvMLP: Hierarchical Convolutional MLPs for Vis...	2021-09-09	Code
61	Proxyless-G + c/o	97.92	No	ProxylessNAS: Direct Neural Architecture Search ...	2018-12-02	Code
62	NAT-M2	97.9	Yes	Neural Architecture Transfer	2020-05-12	Code
63	WRN-28-10+AutoDropout+RandAugment	97.9	No	AutoDropout: Learning Dropout Patterns to Regula...	2021-01-05	Code
64	SENet + ShakeShake + Cutout	97.88	No	Squeeze-and-Excitation Networks	2017-09-05	Code
65	HCGNet-A3	97.86	No	Gated Convolutional Networks with Hybrid Connect...	2019-08-26	Code
66	Wide-ResNet-28-10	97.85	No	Automatic Data Augmentation via Invariance-Const...	2022-09-29	Code
67	ResNeXt-50 (AutoMix)	97.84	No	AutoMix: Unveiling the Power of Mixup for Strong...	2021-03-24	Code
68	ResNet-152x4-AGC (ImageNet-21K)	97.82	No	Effect of Pre-Training Scale on Intra- and Inter...	2021-05-31	Code
69	Mixer-B/16- SAM	97.8	No	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
70	CCT-7/3x1+VTM	97.78	No	TokenMixup: Efficient Attention-guided Token-lev...	2022-10-14	Code
71	WRN-28-10	97.73	No	MixMo: Mixing Multiple Inputs for Multiple Outpu...	2021-03-10	Code
72	HCGNet-A2	97.71	No	Gated Convolutional Networks with Hybrid Connect...	2019-08-26	Code
73	WRN + fixup init + mixup + cutout	97.7	No	Fixup Initialization: Residual Learning Without ...	2019-01-27	Code
74	NoisyDARTS-a	97.61	No	Noisy Differentiable Architecture Search	2020-05-07	Code
75	TransBoost-ResNet50	97.61	No	TransBoost: Improving the Best ImageNet Performa...	2022-05-26	Code
76	LeViT-128	97.6	No	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
77	DenseNet-BC-190 + batchboost	97.54	No	batchboost: regularization for stabilizing train...	2020-01-21	Code
78	LeViT-128S	97.5	Yes	LeViT: a Vision Transformer in ConvNet's Clothin...	2021-04-02	Code
79	Shared WRN	97.47	No	Learning Implicitly Recurrent CNNs Through Param...	2019-02-26	Code
80	Manifold Mixup WRN 28-10	97.45	No	Manifold Mixup: Better Representations by Interp...	2018-06-13	Code
81	WRN 28-14	97.45	No	Neural networks with late-phase weights	2020-07-25	Code
82	SparseSwin	97.43	No	SparseSwin: Swin Transformer with Sparse Transfo...	2023-09-11	Code
83	WRN-28-10 with reSGHMC	97.42	No	Non-convex Learning via Replica Exchange Stochas...	2020-08-12	Code
84	NAT-M1	97.4	Yes	Neural Architecture Transfer	2020-05-12	Code
85	ResNet-50-SAM	97.4	Yes	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
86	DenseNet-BC-190 + Mixup	97.3	Yes	mixup: Beyond Empirical Risk Minimization	2017-10-25	Code
87	kNN-CLIP	97.3	Yes	Revisiting a kNN-based Image Classification Syst...	2022-04-03	-
88	WaveMixLite-144/7	97.29	No	WaveMix: A Resource-efficient Neural Network for...	2022-05-28	Code
89	Transformer local-attention (NesT-B)	97.2	No	Nested Hierarchical Transformer: Towards Accurat...	2021-05-26	Code
90	ShakeShake-2x64d + SWA	97.12	No	Averaging Weights Leads to Wider Optima and Bett...	2018-03-14	Code
91	PyramidNet-200 + CutMix	97.12	No	CutMix: Regularization Strategy to Train Strong ...	2019-05-13	Code
92	Wide-ResNet-40-2	97.05	No	Automatic Data Augmentation via Invariance-Const...	2022-09-29	Code
93	ORN	97.02	No	Oriented Response Networks	2017-01-07	Code
94	WRN-16-8 with reSGHMC	96.87	No	Non-convex Learning via Replica Exchange Stochas...	2020-08-12	Code
95	ResNet_XnIDR	96.87	No	XnODR and XnIDR: Two Accurate and Fast Fully Con...	2021-11-21	Code
96	HCGNet-A1	96.85	No	Gated Convolutional Networks with Hybrid Connect...	2019-08-26	Code
97	WRN 28-10	96.81	No	Neural networks with late-phase weights	2020-07-25	Code
98	AutoDropout	96.8	No	AutoDropout: Learning Dropout Patterns to Regula...	2021-01-05	Code
99	WRN-28-10 + SWA	96.79	No	Averaging Weights Leads to Wider Optima and Bett...	2018-03-14	Code
100	ConvMixer-256/16	96.74	No	Patches Are All You Need?	2022-01-24	Code
101	EXACT (WRN-28-10)	96.73	No	EXACT: How to Train Your Accuracy	2022-05-19	Code
102	Wide ResNet+cutout	96.71	No	Single-bit-per-weight deep convolutional neural ...	2019-07-16	Code
103	Deep pyramidal residual network	96.69	No	Deep Pyramidal Residual Networks	2016-10-10	Code
104	CoPaNet-R-164	96.62	No	Deep Competitive Pathway Networks	2017-09-29	Code
105	DenseNet (DenseNet-BC-190)	96.54	No	Densely Connected Convolutional Networks	2016-08-25	Code
106	SKNet-29 (ResNeXt-29, 16×32d)	96.53	No	Selective Kernel Networks	2019-03-15	Code
107	Fractional MP	96.5	No	Fractional Max-Pooling	2014-12-18	Code
108	PDO-eConv (p8, 4.6M)	96.5	No	PDO-eConvs: Partial Differential Operator Based ...	2020-07-20	Code
109	UPANets	96.47	No	UPANets: Learning from the Universal Pixel Atten...	2021-03-15	Code
110	GAC-SNN	96.46	No	Gated Attention Coding for Training High-perform...	2023-08-12	Code
111	ViT (lightweight, MAE pretrained)	96.41	No	Pre-training of Lightweight Vision Transformers ...	2024-02-06	-
112	NAS-RL	96.4	No	Neural Architecture Search with Reinforcement Le...	2016-11-05	Code
113	VGG11B(2x) + LocalLearning + CO	96.4	No	Training Neural Networks with Local Error Signals	2019-01-20	Code
114	ABNet-2G-R3-Combined	96.378	No	ANDHRA Bandersnatch: Training Neural Networks to...	2024-11-28	Code
115	Residual Gates + WRN	96.35	No	Learning Identity Mappings with Residual Gates	2016-11-04	-
116	PDO-eConv (p8, 2.62M)	96.32	No	PDO-eConvs: Partial Differential Operator Based ...	2020-07-20	Code
117	SimpleNetv2	96.29	No	Towards Principled Design of Deep Convolutional ...	2018-02-17	Code
118	ResNet56 with reSGHMC	96.12	No	Non-convex Learning via Replica Exchange Stochas...	2020-08-12	Code
119	Mixer-S/16- SAM	96.1	No	When Vision Transformers Outperform ResNets with...	2021-06-03	Code
120	ABNet-2G-R3	96.088	No	ANDHRA Bandersnatch: Training Neural Networks to...	2024-11-28	Code
121	PreActResNet18 (AMP)	96.03	No	Regularizing Neural Networks via Adversarial Mod...	2020-10-10	Code
122	ConvMixer-256/8	96.03	No	Patches Are All You Need?	2022-01-24	Code
123	Local Mixup Resnet18	95.97	No	Preventing Manifold Intrusion with Locality: Loc...	2022-01-12	Code
124	ABNet-2G-R2	95.9	No	ANDHRA Bandersnatch: Training Neural Networks to...	2024-11-28	Code
125	ResNet-50x1-ACG (ImageNet-21K)	95.78	No	Effect of Pre-Training Scale on Intra- and Inter...	2021-05-31	Code
126	ResNet18 (FSGDM)	95.66	No	On the Performance Analysis of Momentum Method: ...	2024-11-29	Code
127	ACN	95.6	No	Striving for Simplicity: The All Convolutional Net	2014-12-21	Code
128	Evolution ensemble	95.6	No	Large-Scale Evolution of Image Classifiers	2017-03-03	Code
129	ResNet-18	95.55	No	Benchopt: Reproducible, efficient and collaborat...	2022-06-27	Code
130	ABNet-2G-R1	95.536	No	ANDHRA Bandersnatch: Training Neural Networks to...	2024-11-28	Code
131	SimpleNetv1	95.51	No	Lets keep it simple, Using simple architectures ...	2016-08-22	Code
132	Mobile Net_Sam	95.5	No	MobileNetV2: Inverted Residuals and Linear Bottl...	2018-01-13	Code
133	IM-Loss (ResNet-19)	95.49	No	-	-	-
134	ResNet-1001	95.4	No	Identity Mappings in Deep Residual Networks	2016-03-16	Code
135	ResNet32 with reSGHMC	95.35	No	Non-convex Learning via Replica Exchange Stochas...	2020-08-12	Code
136	ResNet-18+MM+FRL	95.33	No	Learning Class Unique Features in Fine-Grained V...	2020-11-22	-
137	PSN (Modified PLIF Net)	95.32	No	-	-	-
138	CCT-6/3x1	95.29	No	Escaping the Big Data Paradigm with Compact Tran...	2021-04-12	Code
139	MomentumNet	95.18	No	Momentum Residual Neural Networks	2021-02-15	Code
140	Context-Aware Pipeline	95.16	No	-	-	Code
141	SRM-ResNet-56	95.05	No	SRM : A Style-based Recalibration Module for Con...	2019-03-26	Code
142	MixMatch	95.05	No	MixMatch: A Holistic Approach to Semi-Supervised...	2019-05-06	Code
143	WRN-22-8 (Sparse Momentum)	95.04	No	Sparse Networks from Scratch: Faster Training wi...	2019-07-10	Code
144	LP-BNN (ours) + cutout	95.02	No	Encoding the latent posterior of Bayesian Neural...	2020-12-04	Code
145	kEffNet-B0 V2 32ch + H Flip	94.95	No	-	-	Code
146	Prodpoly	94.9	No	Deep Polynomial Neural Networks	2020-06-20	Code
147	ResNet-9	94.79	Yes	CNN Filter DB: An Empirical Investigation of Tra...	2022-03-29	Code
148	Stochastic Depth	94.77	Yes	Deep Networks with Stochastic Depth	2016-03-30	Code
149	VGG-19 with GradInit	94.71	No	GradInit: Learning to Initialize Neural Networks...	2021-02-16	Code
150	ResNet20 with reSGHMC	94.62	No	Non-convex Learning via Replica Exchange Stochas...	2020-08-12	Code
151	PDO-eConv (p6m,0.37M)	94.62	No	PDO-eConvs: Partial Differential Operator Based ...	2020-07-20	Code
152	Evolution	94.6	No	Large-Scale Evolution of Image Classifiers	2017-03-03	Code
153	RL+NT	94.6	No	Efficient Architecture Search by Network Transfo...	2017-07-16	Code
154	Convolutional Performer for Vision (CPV)	94.46	No	Convolutional Xformers for Vision	2022-01-25	Code
155	PreResNet-110	94.4367	No	How to Use Dropout Correctly on Residual Network...	2023-02-13	Code
156	ResNet+ELU	94.4	No	Deep Residual Networks with Exponential Linear U...	2016-04-14	Code
157	Deep Complex	94.4	No	Deep Complex Networks	2017-05-27	Code
158	PDO-eConv (p6,0.36M)	94.35	No	PDO-eConvs: Partial Differential Operator Based ...	2020-07-20	Code
159	Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods	94.29	No	Stochastic Optimization of Plain Convolutional N...	2020-01-24	Code
160	Fitnet4-LSUV	94.2	No	All you need is a good init	2015-11-19	Code
161	R-ExplaiNet-26	94.15	No	Learning local discrete features in explainable-...	2024-10-31	Code
162	ABNet-2G-R0	94.118	No	ANDHRA Bandersnatch: Training Neural Networks to...	2024-11-28	Code
163	ResNet 9 + Mish	94.05	No	Mish: A Self Regularized Non-Monotonic Activatio...	2019-08-23	Code
164	Tree+Max-Avg pooling	94	No	Generalizing Pooling Functions in Convolutional ...	2015-09-30	Code
165	Beta-Rank	93.97	No	Beta-Rank: A Robust Convolutional Filter Pruning...	2023-04-15	Code
166	ResNet-110 (SAP)	93.861	No	Stochastic Subsampling With Average Pooling	2024-09-25	-
167	SA quadratic embedding	93.8	No	On the Relationship between Self-Attention and C...	2019-11-08	Code
168	kEffNet-B0 32ch	93.75	No	-	-	Code
169	OTTT	93.73	No	Online Training Through Time for Spiking Neural ...	2022-10-09	Code
170	SSCNN	93.7	No	Spatially-sparse convolutional neural networks	2014-09-22	Code
171	NNCLR	93.7	No	With a Little Help from My Friends: Nearest-Neig...	2021-04-29	Code
172	Tuned CNN	93.6	No	Scalable Bayesian Optimization Using Deep Neural...	2015-02-19	Code
173	Exponential Linear Units	93.5	No	Fast and Accurate Deep Network Learning by Expon...	2015-11-23	Code
174	BNM NiN	93.3	No	Batch-normalized Maxout Network in Network	2015-11-09	Code
175	Universum Prescription	93.3	No	Universum Prescription: Regularization using Unl...	2015-11-11	-
176	CMsC	93.1	No	Competitive Multi-scale Convolution	2015-11-18	-
177	DGPPF-ResNet18	92.9	No	-	-	Code
178	kMobileNet V3 Large 16ch	92.74	No	-	-	Code
179	NiN+APL	92.5	No	Learning Activation Functions to Improve Deep Ne...	2014-12-21	Code
180	VDN	92.4	No	Training Very Deep Networks	2015-07-22	Code
181	ResNet	92.3	No	A Bregman Learning Framework for Sparse Neural N...	2021-05-10	Code
182	SWWAE	92.2	No	Stacked What-Where Auto-encoders	2015-06-08	Code
183	FlexTCN-7	92.2	No	FlexConv: Continuous Kernel Convolutions with Di...	2021-10-15	Code
184	ReActNet-18	92.08	No	"BNN - BN = ?": Training Binary Neural Networks ...	2021-04-16	Code
185	ResNet v2-20 (Mish activation)	92.02	No	Mish: A Self Regularized Non-Monotonic Activatio...	2019-08-23	Code
186	Context-Aware DNN tree	92.01	No	-	-	-
187	DSN	91.8	No	Deeply-Supervised Nets	2014-09-18	Code
188	BinaryConnect	91.7	No	BinaryConnect: Training Deep Neural Networks wit...	2015-11-02	Code
189	CLS-GAN	91.7	No	Loss-Sensitive Generative Adversarial Networks o...	2017-01-23	Code
190	MIM	91.5	No	On the Importance of Normalisation Layers in Dee...	2015-08-03	-
191	Spectral Representations for Convolutional Neural Networks	91.4	No	Spectral Representations for Convolutional Neura...	2015-06-11	-
192	DLME (ResNet-18, linear)	91.3	No	DLME: Deep Local-flatness Manifold Embedding	2022-07-07	Code
193	RMDL (30 RDLs)	91.21	No	RMDL: Random Multimodel Deep Learning for Classi...	2018-05-03	Code
194	Network in Network	91.2	No	Network In Network	2013-12-16	Code
195	ResNet-26 (Trainable Activations)	91.1	No	-	-	Code
196	ResNet-32 (Trainable Activations)	90.9	No	-	-	Code
197	kDenseNet-BC L100 12ch	90.83	No	-	-	Code
198	Deep Networks with Internal Selective Attention through Feedback Connections	90.8	No	Deep Networks with Internal Selective Attention ...	2014-07-11	-
199	Maxout Network (k=2)	90.65	No	Maxout Networks	2013-02-18	Code
200	ResNet-18	90.65	Yes	Knowledge Representing: Efficient, Sparse Repres...	2019-11-13	-
201	DNN+Probabilistic Maxout	90.6	Yes	Improving Deep Neural Networks with Probabilisti...	2013-12-20	-
202	GP EI	90.5	No	Practical Bayesian Optimization of Machine Learn...	2012-06-13	Code
203	ResNet-44 (Trainable Activations)	90.5	No	-	-	Code
204	ResNet-20 (Trainable Activations)	90.4	No	-	-	Code
205	SEER (RegNet10B)	90	No	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
206	kMobileNet 16ch	89.81	No	-	-	Code
207	APAC	89.7	No	APAC: Augmented PAttern Classification with Neur...	2015-05-13	-
208	ensemble of 7 models	89.4	No	Dynamic Routing Between Capsules	2017-10-26	Code
209	DCNN+GFE	89.1	No	Deep Convolutional Neural Networks as Generic Fe...	2017-10-06	-
210	DCNN	89	No	-	-	Code
211	ResNet-14 (Trainable Activations)	89	No	-	-	Code
212	MCDNN	88.8	No	Multi-column Deep Neural Networks for Image Clas...	2012-02-13	Code
213	RReLU	88.8	No	Empirical Evaluation of Rectified Activations in...	2015-05-05	Code
214	ResNet-56 (Trainable Activations)	88.8	No	-	-	Code
215	F-DENSER++	88.73	No	Fast-DENSER++: Evolving Fully-Trained Deep Artif...	2019-05-08	-
216	Diffusion Classifier (zero-shot)	88.5	No	Your Diffusion Model is Secretly a Zero-Shot Cla...	2023-03-28	Code
217	ReNet	87.7	Yes	ReNet: A Recurrent Neural Network Based Alternat...	2015-05-03	Code
218	OnDev-LCT-8/3	87.65	No	OnDev-LCT: On-Device Lightweight Convolutional T...	2024-01-22	-
219	OnDev-LCT-4/3	87.03	No	OnDev-LCT: On-Device Lightweight Convolutional T...	2024-01-22	-
220	TripleNet-B	87.03	No	Efficient Convolutional Neural Networks on Raspb...	2022-04-02	Code
221	An Analysis of Unsupervised Pre-training in Light of Recent Advances	86.7	No	An Analysis of Unsupervised Pre-training in Ligh...	2014-12-20	Code
222	ThreshNet95	86.69	No	ThreshNet: An Efficient DenseNet Using Threshold...	2022-01-09	Code
223	OnDev-LCT-8/1	86.64	No	OnDev-LCT: On-Device Lightweight Convolutional T...	2024-01-22	-
224	ShortNet1-53	86.64	No	Connection Reduction of DenseNet for Image Recog...	2022-08-02	Code
225	OnDev-LCT-4/1	86.61	No	OnDev-LCT: On-Device Lightweight Convolutional T...	2024-01-22	-
226	CNN+ Wilson-Cowan model RNN	86.59	No	Learning in Wilson-Cowan model for metapopulation	2024-06-24	Code
227	ResNet-8 (Trainable Activations)	86.5	No	-	-	Code
228	ThresholdNet	86.34	No	New Pruning Method Based on DenseNet Network for...	2021-08-28	-
229	OnDev-LCT-2/1	86.27	No	OnDev-LCT: On-Device Lightweight Convolutional T...	2024-01-22	-
230	OnDev-LCT-2/3	86.04	No	OnDev-LCT: On-Device Lightweight Convolutional T...	2024-01-22	-
231	OnDev-LCT-1/3	85.73	No	OnDev-LCT: On-Device Lightweight Convolutional T...	2024-01-22	-
232	cvpr_class	85.28	No	ResNet strikes back: An improved training proced...	2021-10-01	Code
233	WaveMix	85.21	No	-	-	Code
234	Stochastic Pooling	84.9	No	Stochastic Pooling for Regularization of Deep Co...	2013-01-16	Code
235	OnDev-LCT-1/1	84.55	No	OnDev-LCT: On-Device Lightweight Convolutional T...	2024-01-22	-
236	Improving neural networks by preventing co-adaptation of feature detectors	84.4	No	Improving neural networks by preventing co-adapt...	2012-07-03	Code
237	CCN	83.36	Yes	Vision Xformers: Efficient Attention for Image C...	2021-07-05	Code
238	CvN	83.26	Yes	Vision Xformers: Efficient Attention for Image C...	2021-07-05	Code
239	UL-Hopfield (ULH)	83.1	No	Unsupervised Learning using Pretrained CNN and A...	2018-05-02	-
240	DCGAN	82.8	Yes	Unsupervised Representation Learning with Deep C...	2015-11-19	Code
241	TM Composites Toolbox	82.8	Yes	An Optimized Toolbox for Advanced Image Processi...	2024-06-02	Code
242	CKN	82.2	No	Convolutional Kernel Networks	2014-06-12	-
243	The Analog Activation Function	82.06	No	-	-	Code
244	Discriminative Unsupervised Feature Learning with Convolutional Neural Networks	82	No	-	-	Code
245	Sign-symmetry	80.98	Yes	How Important is Weight Symmetry in Backpropagat...	2015-10-17	Code
246	pFedBreD_ns_mg	80.63	No	Personalized Federated Learning with Hidden Info...	2022-11-19	-
247	1 Layer K-means	80.6	No	Unsupervised Representation Learning with Deep C...	2015-11-19	Code
248	APVT	80.45	No	Aggregated Pyramid Vision Transformer: Split-tra...	2022-03-02	-
249	Learning with Recursive Perceptual Representations	79.7	No	-	-	-
250	LeViP	79.5	No	Vision Xformers: Efficient Attention for Image C...	2021-07-05	Code
251	Convolutional Deep Belief Network	78.9	No	-	-	-
252	PCANet	78.7	No	PCANet: A Simple Deep Learning Baseline for Imag...	2014-04-14	Code
253	Hybrid ViT+RoPE	76.9	No	Vision Xformers: Efficient Attention for Image C...	2021-07-05	Code
254	FLSCNN	75.9	No	Enhanced Image Classification With a Fast-Learni...	2015-03-16	-
255	Hybrid Vision Nystromformer (ViN)	75.26	No	Vision Xformers: Efficient Attention for Image C...	2021-07-05	Code
256	CTM Drop Clause	75.1	No	Drop Clause: Enhancing Performance, Interpretabi...	2021-05-30	Code
257	Hybrid PiN	74	No	Vision Xformers: Efficient Attention for Image C...	2021-07-05	Code
258	SmoothNetV1	73.5	No	SmoothNets: Optimizing CNN architecture design f...	2022-05-09	Code
259	SNN	68.3	No	Sneaky Spikes: Uncovering Stealthy Backdoor Atta...	2023-02-13	Code
260	Vision Nystromformer (ViN)	65.06	No	Vision Xformers: Efficient Attention for Image C...	2021-07-05	Code
261	ANODE	60.6	No	Augmented Neural ODEs	2019-04-02	Code

#1ViT-H/14SOTA
99.5
Percentage correct· Extra Data· 2020-10-22
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale Code
#2DINOv2 (ViT-g/14, frozen model, linear eval)
99.5
Percentage correct· Extra Data· 2023-04-14
DINOv2: Learning Robust Visual Features without Supervision Code
#3µ2Net (ViT-L/16)
99.49
Percentage correct· Extra Data· 2022-05-25
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems Code
#4ViT-L/16
99.42
Percentage correct· Extra Data· 2020-10-22
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale Code
#5CaiT-M-36 U 224
99.4
Percentage correct· Extra Data· 2021-03-31
Going deeper with Image Transformers Code
#6CvT-W24
99.39
Percentage correct· Extra Data· 2021-03-29
CvT: Introducing Convolutions to Vision Transformers Code
#7BiT-L (ResNet)SOTA
99.37
Percentage correct· Extra Data· 2019-12-24
Big Transfer (BiT): General Visual Representation Learning Code
#8RDNet-L (224 res, IN-1K pretrained)
99.31
Percentage correct· Extra Data· 2024-03-28
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs Code
#9RDNet-B (224 res, IN-1K pretrained)
99.31
Percentage correct· Extra Data· 2024-03-28
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs Code
#10ViT-B (attn fine-tune)
99.3
Percentage correct· Extra Data· 2022-03-18
Three things everyone should know about Vision Transformers Code
#11Heinsen Routing + BEiT-large 16 224
99.2
Percentage correct· Extra Data· 2022-11-20
An Algorithm for Routing Vectors in Sequences Code
#12ViT-B/16 (PUGD)
99.13
Percentage correct· Extra Data· 2021-10-01
Perturbated Gradients Updating within Unit Space for Deep Learning Code
#13Astroformer
99.12
Percentage correct· Extra Data· 2023-04-03
Astroformer: More Data Might not be all you need for Classification Code
#14DeiT-B
99.1
Percentage correct· Extra Data· 2020-12-23
Training data-efficient image transformers & distillation through attention Code
#15TNT-B
99.1
Percentage correct· Extra Data· 2021-02-27
Transformer in Transformer Code
#16CeiT-S (384 finetune resolution)
99.1
Percentage correct· Extra Data· 2021-03-22
Incorporating Convolution Designs into Visual Transformers Code
#17EfficientNetV2-L
99.1
Percentage correct· Extra Data· 2021-04-01
EfficientNetV2: Smaller Models and Faster Training Code
#18AutoFormer-S | 384
99.1
Percentage correct· Extra Data· 2021-07-01
AutoFormer: Searching Transformers for Visual Recognition Code
#19VIT-L/16 (Spinal FC, Background)
99.05
Percentage correct· 2023-05-05
Reduction of Class Activation Uncertainty with Background Information Code
#20LaNet
99.03
Percentage correct
No paperCode
#21GPIPE + transfer learningSOTA
99
Percentage correct· Extra Data· 2018-11-16
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism Code
#22TResNet-XL
99
Percentage correct· 2020-03-30
TResNet: High Performance GPU-Dedicated Architecture Code
#23CeiT-S
99
Percentage correct· 2021-03-22
Incorporating Convolution Designs into Visual Transformers Code
#24EfficientNetV2-M
99
Percentage correct· 2021-04-01
EfficientNetV2: Smaller Models and Faster Training Code
#25GFNet-H-B
99
Percentage correct· Extra Data· 2021-07-01
Global Filter Networks for Image Classification Code
#26BiT-M (ResNet)
98.91
Percentage correct· 2019-12-24
Big Transfer (BiT): General Visual Representation Learning Code
#27EfficientNet-B7
98.9
Percentage correct· 2019-05-28
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks Code
#28RDNet-T (224 res, IN-1K pretrained)
98.88
Percentage correct· 2024-03-28
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs Code
#29PyramidNet-272, S=4
98.71
Percentage correct· 2020-11-30
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training Code
#30EfficientNetV2-S
98.7
Percentage correct· 2021-04-01
EfficientNetV2: Smaller Models and Faster Training Code
#31ASF-former-S
98.7
Percentage correct· 2022-04-26
Adaptive Split-Fusion Transformer Code
#32PyramidNet-272 (ASAM)
98.68
Percentage correct· 2021-02-23
ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks Code
#33PyramidNet + ShakeDrop + Fast AA + FMix
98.64
Percentage correct· 2020-02-27
FMix: Enhancing Mixed Sample Data Augmentation Code
#34ViT-B/16- SAM
98.6
Percentage correct· 2021-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Code
#35ConvMLP-M
98.6
Percentage correct· Extra Data· 2021-09-09
ConvMLP: Hierarchical Convolutional MLPs for Vision Code
#36ConvMLP-L
98.6
Percentage correct· Extra Data· 2021-09-09
ConvMLP: Hierarchical Convolutional MLPs for Vision Code
#37DVT (T2T-ViT-24)
98.53
Percentage correct· 2021-05-31
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition Code
#38E2E-3M
98.52
Percentage correct· 2020-07-30
Rethinking Recurrent Neural Networks and Other Improvements for Image Classification Code
#39CeiT-T
98.5
Percentage correct· 2021-03-22
Incorporating Convolution Designs into Visual Transformers Code
#40NAT-M4
98.4
Percentage correct· Extra Data· 2020-05-12
Neural Architecture Transfer Code
#41WRN-40-10, S=4
98.38
Percentage correct· 2020-11-30
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training Code
#42WRN-28-10, S=4
98.32
Percentage correct· 2020-11-30
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training Code
#43Shake-Shake 26 2x96d, S=4
98.31
Percentage correct· 2020-11-30
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training Code
#44Dynamics 2
98.31
Percentage correct· 2022-05-20
PSO-Convolutional Neural Networks with Heterogeneous Learning Rate Code
#45PyramidNet+ShakeDrop (Fast AA)
98.3
Percentage correct· 2019-05-01
Fast AutoAugment Code
#46ResNet50 (A1)
98.3
Percentage correct· 2021-10-01
ResNet strikes back: An improved training procedure in timm Code
#47NoisyDARTS-A-t
98.28
Percentage correct· 2020-05-07
Noisy Differentiable Architecture Search Code
#48NAT-M3
98.2
Percentage correct· Extra Data· 2020-05-12
Neural Architecture Transfer Code
#49LeViT-192
98.2
Percentage correct· 2021-04-02
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference Code
#50ResNet-152-SAM
98.2
Percentage correct· 2021-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Code
#51ViT-S/16- SAM
98.2
Percentage correct· 2021-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Code
#52Bamboo (ViT-B/16)
98.2
Percentage correct· 2022-03-15
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy Code
#53DE ELBo (ViT-B/16)
98.2
Percentage correct· 2025-02-03
Learning Hyperparameters via a Data-Emphasized Variational Objective Code
#54LeViT-256
98.1
Percentage correct· Extra Data· 2021-04-02
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference Code
#55PyramidNet + AA (AMP)
98.02
Percentage correct· 2020-10-10
Regularizing Neural Networks via Adversarial Model Perturbation Code
#56EnAET
98.01
Percentage correct· 2019-11-21
EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations Code
#57MUXNet-m
98
Percentage correct· 2020-03-31
MUXConv: Information Multiplexing in Convolutional Neural Networks Code
#58LeViT-384
98
Percentage correct· 2021-04-02
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference Code
#59CCT-7/3x1*
98
Percentage correct· 2021-04-12
Escaping the Big Data Paradigm with Compact Transformers Code
#60ConvMLP-S
98
Percentage correct· Extra Data· 2021-09-09
ConvMLP: Hierarchical Convolutional MLPs for Vision Code
#61Proxyless-G + c/o
97.92
Percentage correct· 2018-12-02
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware Code
#62NAT-M2
97.9
Percentage correct· Extra Data· 2020-05-12
Neural Architecture Transfer Code
#63WRN-28-10+AutoDropout+RandAugment
97.9
Percentage correct· 2021-01-05
AutoDropout: Learning Dropout Patterns to Regularize Deep Networks Code
#64SENet + ShakeShake + CutoutSOTA
97.88
Percentage correct· 2017-09-05
Squeeze-and-Excitation Networks Code
#65HCGNet-A3
97.86
Percentage correct· 2019-08-26
Gated Convolutional Networks with Hybrid Connectivity for Image Classification Code
#66Wide-ResNet-28-10
97.85
Percentage correct· 2022-09-29
Automatic Data Augmentation via Invariance-Constrained Learning Code
#67ResNeXt-50 (AutoMix)
97.84
Percentage correct· 2021-03-24
AutoMix: Unveiling the Power of Mixup for Stronger Classifiers Code
#68ResNet-152x4-AGC (ImageNet-21K)
97.82
Percentage correct· 2021-05-31
Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images Code
#69Mixer-B/16- SAM
97.8
Percentage correct· 2021-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Code
#70CCT-7/3x1+VTM
97.78
Percentage correct· 2022-10-14
TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers Code
#71WRN-28-10
97.73
Percentage correct· 2021-03-10
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks Code
#72HCGNet-A2
97.71
Percentage correct· 2019-08-26
Gated Convolutional Networks with Hybrid Connectivity for Image Classification Code
#73WRN + fixup init + mixup + cutout
97.7
Percentage correct· 2019-01-27
Fixup Initialization: Residual Learning Without Normalization Code
#74NoisyDARTS-a
97.61
Percentage correct· 2020-05-07
Noisy Differentiable Architecture Search Code
#75TransBoost-ResNet50
97.61
Percentage correct· 2022-05-26
TransBoost: Improving the Best ImageNet Performance using Deep Transduction Code
#76LeViT-128
97.6
Percentage correct· 2021-04-02
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference Code
#77DenseNet-BC-190 + batchboost
97.54
Percentage correct· 2020-01-21
batchboost: regularization for stabilizing training with resistance to underfitting & overfitting Code
#78LeViT-128S
97.5
Percentage correct· Extra Data· 2021-04-02
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference Code
#79Shared WRN
97.47
Percentage correct· 2019-02-26
Learning Implicitly Recurrent CNNs Through Parameter Sharing Code
#80Manifold Mixup WRN 28-10
97.45
Percentage correct· 2018-06-13
Manifold Mixup: Better Representations by Interpolating Hidden States Code
#81WRN 28-14
97.45
Percentage correct· 2020-07-25
Neural networks with late-phase weights Code
#82SparseSwin
97.43
Percentage correct· 2023-09-11
SparseSwin: Swin Transformer with Sparse Transformer Block Code
#83WRN-28-10 with reSGHMC
97.42
Percentage correct· 2020-08-12
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC Code
#84NAT-M1
97.4
Percentage correct· Extra Data· 2020-05-12
Neural Architecture Transfer Code
#85ResNet-50-SAM
97.4
Percentage correct· Extra Data· 2021-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Code
#86DenseNet-BC-190 + Mixup
97.3
Percentage correct· Extra Data· 2017-10-25
mixup: Beyond Empirical Risk Minimization Code
#87kNN-CLIP
97.3
Percentage correct· Extra Data· 2022-04-03
Revisiting a kNN-based Image Classification System with High-capacity Storage
#88WaveMixLite-144/7
97.29
Percentage correct· 2022-05-28
WaveMix: A Resource-efficient Neural Network for Image Analysis Code
#89Transformer local-attention (NesT-B)
97.2
Percentage correct· 2021-05-26
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding Code
#90ShakeShake-2x64d + SWA
97.12
Percentage correct· 2018-03-14
Averaging Weights Leads to Wider Optima and Better Generalization Code
#91PyramidNet-200 + CutMix
97.12
Percentage correct· 2019-05-13
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features Code
#92Wide-ResNet-40-2
97.05
Percentage correct· 2022-09-29
Automatic Data Augmentation via Invariance-Constrained Learning Code
#93ORNSOTA
97.02
Percentage correct· 2017-01-07
Oriented Response Networks Code
#94WRN-16-8 with reSGHMC
96.87
Percentage correct· 2020-08-12
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC Code
#95ResNet_XnIDR
96.87
Percentage correct· 2021-11-21
XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks Code
#96HCGNet-A1
96.85
Percentage correct· 2019-08-26
Gated Convolutional Networks with Hybrid Connectivity for Image Classification Code
#97WRN 28-10
96.81
Percentage correct· 2020-07-25
Neural networks with late-phase weights Code
#98AutoDropout
96.8
Percentage correct· 2021-01-05
AutoDropout: Learning Dropout Patterns to Regularize Deep Networks Code
#99WRN-28-10 + SWA
96.79
Percentage correct· 2018-03-14
Averaging Weights Leads to Wider Optima and Better Generalization Code
#100ConvMixer-256/16
96.74
Percentage correct· 2022-01-24
Patches Are All You Need?Code
#101EXACT (WRN-28-10)
96.73
Percentage correct· 2022-05-19
EXACT: How to Train Your Accuracy Code
#102Wide ResNet+cutout
96.71
Percentage correct· 2019-07-16
Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systems Code
#103Deep pyramidal residual networkSOTA
96.69
Percentage correct· 2016-10-10
Deep Pyramidal Residual Networks Code
#104CoPaNet-R-164
96.62
Percentage correct· 2017-09-29
Deep Competitive Pathway Networks Code
#105DenseNet (DenseNet-BC-190)SOTA
96.54
Percentage correct· 2016-08-25
Densely Connected Convolutional Networks Code
#106SKNet-29 (ResNeXt-29, 16×32d)
96.53
Percentage correct· 2019-03-15
Selective Kernel Networks Code
#107Fractional MPSOTA
96.5
Percentage correct· 2014-12-18
Fractional Max-Pooling Code
#108PDO-eConv (p8, 4.6M)
96.5
Percentage correct· 2020-07-20
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions Code
#109UPANets
96.47
Percentage correct· 2021-03-15
UPANets: Learning from the Universal Pixel Attention Networks Code
#110GAC-SNN
96.46
Percentage correct· 2023-08-12
Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networks Code
#111ViT (lightweight, MAE pretrained)
96.41
Percentage correct· 2024-02-06
Pre-training of Lightweight Vision Transformers on Small Datasets with Minimally Scaled Images
#112NAS-RL
96.4
Percentage correct· 2016-11-05
Neural Architecture Search with Reinforcement Learning Code
#113VGG11B(2x) + LocalLearning + CO
96.4
Percentage correct· 2019-01-20
Training Neural Networks with Local Error Signals Code
#114ABNet-2G-R3-Combined
96.378
Percentage correct· 2024-11-28
ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities Code
#115Residual Gates + WRN
96.35
Percentage correct· 2016-11-04
Learning Identity Mappings with Residual Gates
#116PDO-eConv (p8, 2.62M)
96.32
Percentage correct· 2020-07-20
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions Code
#117SimpleNetv2
96.29
Percentage correct· 2018-02-17
Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet Code
#118ResNet56 with reSGHMC
96.12
Percentage correct· 2020-08-12
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC Code
#119Mixer-S/16- SAM
96.1
Percentage correct· 2021-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Code
#120ABNet-2G-R3
96.088
Percentage correct· 2024-11-28
ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities Code
#121PreActResNet18 (AMP)
96.03
Percentage correct· 2020-10-10
Regularizing Neural Networks via Adversarial Model Perturbation Code
#122ConvMixer-256/8
96.03
Percentage correct· 2022-01-24
Patches Are All You Need?Code
#123Local Mixup Resnet18
95.97
Percentage correct· 2022-01-12
Preventing Manifold Intrusion with Locality: Local Mixup Code
#124ABNet-2G-R2
95.9
Percentage correct· 2024-11-28
ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities Code
#125ResNet-50x1-ACG (ImageNet-21K)
95.78
Percentage correct· 2021-05-31
Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images Code
#126ResNet18 (FSGDM)
95.66
Percentage correct· 2024-11-29
On the Performance Analysis of Momentum Method: A Frequency Domain Perspective Code
#127ACN
95.6
Percentage correct· 2014-12-21
Striving for Simplicity: The All Convolutional Net Code
#128Evolution ensemble
95.6
Percentage correct· 2017-03-03
Large-Scale Evolution of Image Classifiers Code
#129ResNet-18
95.55
Percentage correct· 2022-06-27
Benchopt: Reproducible, efficient and collaborative optimization benchmarks Code
#130ABNet-2G-R1
95.536
Percentage correct· 2024-11-28
ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities Code
#131SimpleNetv1
95.51
Percentage correct· 2016-08-22
Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures Code
#132Mobile Net_Sam
95.5
Percentage correct· 2018-01-13
MobileNetV2: Inverted Residuals and Linear Bottlenecks Code
#133IM-Loss (ResNet-19)
95.49
Percentage correct
No paper
#134ResNet-1001
95.4
Percentage correct· 2016-03-16
Identity Mappings in Deep Residual Networks Code
#135ResNet32 with reSGHMC
95.35
Percentage correct· 2020-08-12
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC Code
#136ResNet-18+MM+FRL
95.33
Percentage correct· 2020-11-22
Learning Class Unique Features in Fine-Grained Visual Classification
#137PSN (Modified PLIF Net)
95.32
Percentage correct
No paper
#138CCT-6/3x1
95.29
Percentage correct· 2021-04-12
Escaping the Big Data Paradigm with Compact Transformers Code
#139MomentumNet
95.18
Percentage correct· 2021-02-15
Momentum Residual Neural Networks Code
#140Context-Aware Pipeline
95.16
Percentage correct
No paperCode
#141SRM-ResNet-56
95.05
Percentage correct· 2019-03-26
SRM : A Style-based Recalibration Module for Convolutional Neural Networks Code
#142MixMatch
95.05
Percentage correct· 2019-05-06
MixMatch: A Holistic Approach to Semi-Supervised Learning Code
#143WRN-22-8 (Sparse Momentum)
95.04
Percentage correct· 2019-07-10
Sparse Networks from Scratch: Faster Training without Losing Performance Code
#144LP-BNN (ours) + cutout
95.02
Percentage correct· 2020-12-04
Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification Code
#145kEffNet-B0 V2 32ch + H Flip
94.95
Percentage correct
No paperCode
#146Prodpoly
94.9
Percentage correct· 2020-06-20
Deep Polynomial Neural Networks Code
#147ResNet-9
94.79
Percentage correct· Extra Data· 2022-03-29
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters Code
#148Stochastic Depth
94.77
Percentage correct· Extra Data· 2016-03-30
Deep Networks with Stochastic Depth Code
#149VGG-19 with GradInit
94.71
Percentage correct· 2021-02-16
GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training Code
#150ResNet20 with reSGHMC
94.62
Percentage correct· 2020-08-12
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC Code
#151PDO-eConv (p6m,0.37M)
94.62
Percentage correct· 2020-07-20
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions Code
#152Evolution
94.6
Percentage correct· 2017-03-03
Large-Scale Evolution of Image Classifiers Code
#153RL+NT
94.6
Percentage correct· 2017-07-16
Efficient Architecture Search by Network Transformation Code
#154Convolutional Performer for Vision (CPV)
94.46
Percentage correct· 2022-01-25
Convolutional Xformers for Vision Code
#155PreResNet-110
94.4367
Percentage correct· 2023-02-13
How to Use Dropout Correctly on Residual Networks with Batch Normalization Code
#156ResNet+ELU
94.4
Percentage correct· 2016-04-14
Deep Residual Networks with Exponential Linear Unit Code
#157Deep Complex
94.4
Percentage correct· 2017-05-27
Deep Complex Networks Code
#158PDO-eConv (p6,0.36M)
94.35
Percentage correct· 2020-07-20
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions Code
#159Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods
94.29
Percentage correct· 2020-01-24
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods Code
#160Fitnet4-LSUV
94.2
Percentage correct· 2015-11-19
All you need is a good init Code
#161R-ExplaiNet-26
94.15
Percentage correct· 2024-10-31
Learning local discrete features in explainable-by-design convolutional neural networks Code
#162ABNet-2G-R0
94.118
Percentage correct· 2024-11-28
ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities Code
#163ResNet 9 + Mish
94.05
Percentage correct· 2019-08-23
Mish: A Self Regularized Non-Monotonic Activation Function Code
#164Tree+Max-Avg pooling
94
Percentage correct· 2015-09-30
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree Code
#165Beta-Rank
93.97
Percentage correct· 2023-04-15
Beta-Rank: A Robust Convolutional Filter Pruning Method For Imbalanced Medical Image Analysis Code
#166ResNet-110 (SAP)
93.861
Percentage correct· 2024-09-25
Stochastic Subsampling With Average Pooling
#167SA quadratic embedding
93.8
Percentage correct· 2019-11-08
On the Relationship between Self-Attention and Convolutional Layers Code
#168kEffNet-B0 32ch
93.75
Percentage correct
No paperCode
#169OTTT
93.73
Percentage correct· 2022-10-09
Online Training Through Time for Spiking Neural Networks Code
#170SSCNNSOTA
93.7
Percentage correct· 2014-09-22
Spatially-sparse convolutional neural networks Code
#171NNCLR
93.7
Percentage correct· 2021-04-29
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations Code
#172Tuned CNN
93.6
Percentage correct· 2015-02-19
Scalable Bayesian Optimization Using Deep Neural Networks Code
#173Exponential Linear Units
93.5
Percentage correct· 2015-11-23
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)Code
#174BNM NiN
93.3
Percentage correct· 2015-11-09
Batch-normalized Maxout Network in Network Code
#175Universum Prescription
93.3
Percentage correct· 2015-11-11
Universum Prescription: Regularization using Unlabeled Data
#176CMsC
93.1
Percentage correct· 2015-11-18
Competitive Multi-scale Convolution
#177DGPPF-ResNet18
92.9
Percentage correct
No paperCode
#178kMobileNet V3 Large 16ch
92.74
Percentage correct
No paperCode
#179NiN+APL
92.5
Percentage correct· 2014-12-21
Learning Activation Functions to Improve Deep Neural Networks Code
#180VDN
92.4
Percentage correct· 2015-07-22
Training Very Deep Networks Code
#181ResNet
92.3
Percentage correct· 2021-05-10
A Bregman Learning Framework for Sparse Neural Networks Code
#182SWWAE
92.2
Percentage correct· 2015-06-08
Stacked What-Where Auto-encoders Code
#183FlexTCN-7
92.2
Percentage correct· 2021-10-15
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes Code
#184ReActNet-18
92.08
Percentage correct· 2021-04-16
"BNN - BN = ?": Training Binary Neural Networks without Batch Normalization Code
#185ResNet v2-20 (Mish activation)
92.02
Percentage correct· 2019-08-23
Mish: A Self Regularized Non-Monotonic Activation Function Code
#186Context-Aware DNN tree
92.01
Percentage correct
No paper
#187DSNSOTA
91.8
Percentage correct· 2014-09-18
Deeply-Supervised Nets Code
#188BinaryConnect
91.7
Percentage correct· 2015-11-02
BinaryConnect: Training Deep Neural Networks with binary weights during propagations Code
#189CLS-GAN
91.7
Percentage correct· 2017-01-23
Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities Code
#190MIM
91.5
Percentage correct· 2015-08-03
On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units
#191Spectral Representations for Convolutional Neural Networks
91.4
Percentage correct· 2015-06-11
Spectral Representations for Convolutional Neural Networks
#192DLME (ResNet-18, linear)
91.3
Percentage correct· 2022-07-07
DLME: Deep Local-flatness Manifold Embedding Code
#193RMDL (30 RDLs)
91.21
Percentage correct· 2018-05-03
RMDL: Random Multimodel Deep Learning for Classification Code
#194Network in NetworkSOTA
91.2
Percentage correct· 2013-12-16
Network In Network Code
#195ResNet-26 (Trainable Activations)
91.1
Percentage correct
No paperCode
#196ResNet-32 (Trainable Activations)
90.9
Percentage correct
No paperCode
#197kDenseNet-BC L100 12ch
90.83
Percentage correct
No paperCode
#198Deep Networks with Internal Selective Attention through Feedback Connections
90.8
Percentage correct· 2014-07-11
Deep Networks with Internal Selective Attention through Feedback Connections
#199Maxout Network (k=2)SOTA
90.65
Percentage correct· 2013-02-18
Maxout Networks Code
#200ResNet-18
90.65
Percentage correct· Extra Data· 2019-11-13
Knowledge Representing: Efficient, Sparse Representation of Prior Knowledge for Knowledge Distillation
#201DNN+Probabilistic Maxout
90.6
Percentage correct· Extra Data· 2013-12-20
Improving Deep Neural Networks with Probabilistic Maxout Units
#202GP EISOTA
90.5
Percentage correct· 2012-06-13
Practical Bayesian Optimization of Machine Learning Algorithms Code
#203ResNet-44 (Trainable Activations)
90.5
Percentage correct
No paperCode
#204ResNet-20 (Trainable Activations)
90.4
Percentage correct
No paperCode
#205SEER (RegNet10B)
90
Percentage correct· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code
#206kMobileNet 16ch
89.81
Percentage correct
No paperCode
#207APAC
89.7
Percentage correct· 2015-05-13
APAC: Augmented PAttern Classification with Neural Networks
#208ensemble of 7 models
89.4
Percentage correct· 2017-10-26
Dynamic Routing Between Capsules Code
#209DCNN+GFE
89.1
Percentage correct· 2017-10-06
Deep Convolutional Neural Networks as Generic Feature Extractors
#210DCNN
89
Percentage correct
No paperCode
#211ResNet-14 (Trainable Activations)
89
Percentage correct
No paperCode
#212MCDNNSOTA
88.8
Percentage correct· 2012-02-13
Multi-column Deep Neural Networks for Image Classification Code
#213RReLU
88.8
Percentage correct· 2015-05-05
Empirical Evaluation of Rectified Activations in Convolutional Network Code
#214ResNet-56 (Trainable Activations)
88.8
Percentage correct
No paperCode
#215F-DENSER++
88.73
Percentage correct· 2019-05-08
Fast-DENSER++: Evolving Fully-Trained Deep Artificial Neural Networks
#216Diffusion Classifier (zero-shot)
88.5
Percentage correct· 2023-03-28
Your Diffusion Model is Secretly a Zero-Shot Classifier Code
#217ReNet
87.7
Percentage correct· Extra Data· 2015-05-03
ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks Code
#218OnDev-LCT-8/3
87.65
Percentage correct· 2024-01-22
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
#219OnDev-LCT-4/3
87.03
Percentage correct· 2024-01-22
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
#220TripleNet-B
87.03
Percentage correct· 2022-04-02
Efficient Convolutional Neural Networks on Raspberry Pi for Image Classification Code
#221An Analysis of Unsupervised Pre-training in Light of Recent Advances
86.7
Percentage correct· 2014-12-20
An Analysis of Unsupervised Pre-training in Light of Recent Advances Code
#222ThreshNet95
86.69
Percentage correct· 2022-01-09
ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections Code
#223OnDev-LCT-8/1
86.64
Percentage correct· 2024-01-22
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
#224ShortNet1-53
86.64
Percentage correct· 2022-08-02
Connection Reduction of DenseNet for Image Recognition Code
#225OnDev-LCT-4/1
86.61
Percentage correct· 2024-01-22
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
#226CNN+ Wilson-Cowan model RNN
86.59
Percentage correct· 2024-06-24
Learning in Wilson-Cowan model for metapopulation Code
#227ResNet-8 (Trainable Activations)
86.5
Percentage correct
No paperCode
#228ThresholdNet
86.34
Percentage correct· 2021-08-28
New Pruning Method Based on DenseNet Network for Image Classification
#229OnDev-LCT-2/1
86.27
Percentage correct· 2024-01-22
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
#230OnDev-LCT-2/3
86.04
Percentage correct· 2024-01-22
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
#231OnDev-LCT-1/3
85.73
Percentage correct· 2024-01-22
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
#232cvpr_class
85.28
Percentage correct· 2021-10-01
ResNet strikes back: An improved training procedure in timm Code
#233WaveMix
85.21
Percentage correct
No paperCode
#234Stochastic Pooling
84.9
Percentage correct· 2013-01-16
Stochastic Pooling for Regularization of Deep Convolutional Neural Networks Code
#235OnDev-LCT-1/1
84.55
Percentage correct· 2024-01-22
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
#236Improving neural networks by preventing co-adaptation of feature detectors
84.4
Percentage correct· 2012-07-03
Improving neural networks by preventing co-adaptation of feature detectors Code
#237CCN
83.36
Percentage correct· Extra Data· 2021-07-05
Vision Xformers: Efficient Attention for Image Classification Code
#238CvN
83.26
Percentage correct· Extra Data· 2021-07-05
Vision Xformers: Efficient Attention for Image Classification Code
#239UL-Hopfield (ULH)
83.1
Percentage correct· 2018-05-02
Unsupervised Learning using Pretrained CNN and Associative Memory Bank
#240DCGAN
82.8
Percentage correct· Extra Data· 2015-11-19
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Code
#241TM Composites Toolbox
82.8
Percentage correct· Extra Data· 2024-06-02
An Optimized Toolbox for Advanced Image Processing with Tsetlin Machine Composites Code
#242CKN
82.2
Percentage correct· 2014-06-12
Convolutional Kernel Networks
#243The Analog Activation Function
82.06
Percentage correct
No paperCode
#244Discriminative Unsupervised Feature Learning with Convolutional Neural Networks
82
Percentage correct
No paperCode
#245Sign-symmetry
80.98
Percentage correct· Extra Data· 2015-10-17
How Important is Weight Symmetry in Backpropagation?Code
#246pFedBreD_ns_mg
80.63
Percentage correct· 2022-11-19
Personalized Federated Learning with Hidden Information on Personalized Prior
#2471 Layer K-means
80.6
Percentage correct· 2015-11-19
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Code
#248APVT
80.45
Percentage correct· 2022-03-02
Aggregated Pyramid Vision Transformer: Split-transform-merge Strategy for Image Recognition without Convolutions
#249Learning with Recursive Perceptual Representations
79.7
Percentage correct
No paper
#250LeViP
79.5
Percentage correct· 2021-07-05
Vision Xformers: Efficient Attention for Image Classification Code
#251Convolutional Deep Belief Network
78.9
Percentage correct
No paper
#252PCANet
78.7
Percentage correct· 2014-04-14
PCANet: A Simple Deep Learning Baseline for Image Classification?Code
#253Hybrid ViT+RoPE
76.9
Percentage correct· 2021-07-05
Vision Xformers: Efficient Attention for Image Classification Code
#254FLSCNN
75.9
Percentage correct· 2015-03-16
Enhanced Image Classification With a Fast-Learning Shallow Convolutional Neural Network
#255Hybrid Vision Nystromformer (ViN)
75.26
Percentage correct· 2021-07-05
Vision Xformers: Efficient Attention for Image Classification Code
#256CTM Drop Clause
75.1
Percentage correct· 2021-05-30
Drop Clause: Enhancing Performance, Interpretability and Robustness of the Tsetlin Machine Code
#257Hybrid PiN
74
Percentage correct· 2021-07-05
Vision Xformers: Efficient Attention for Image Classification Code
#258SmoothNetV1
73.5
Percentage correct· 2022-05-09
SmoothNets: Optimizing CNN architecture design for differentially private deep learning Code
#259SNN
68.3
Percentage correct· 2023-02-13
Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data Code
#260Vision Nystromformer (ViN)
65.06
Percentage correct· 2021-07-05
Vision Xformers: Efficient Attention for Image Classification Code
#261ANODE
60.6
Percentage correct· 2019-04-02
Augmented Neural ODEs Code