| 1 | ViTPose (ViTAE-G, ensemble) | 95 | No | ViTPose: Simple Vision Transformer Baselines for... | 2022-04-26 | Code |
| 2 | ViTPose (ViTAE-G) | 94.8 | No | ViTPose: Simple Vision Transformer Baselines for... | 2022-04-26 | Code |
| 3 | 4xRSN-50 (ensemble) | 94.4 | No | Learning Delicate Local Representations for Mult... | 2020-03-09 | Code |
| 4 | 4xRSN-50 | 94.3 | No | Learning Delicate Local Representations for Mult... | 2020-03-09 | Code |
| 5 | CCM+ | 93.8 | No | Towards High Performance Human Keypoint Detection | 2020-02-03 | Code |
| 6 | UDP-Pose-PSA(384x288) | 93.6 | No | Polarized Self-Attention: Towards High-quality P... | 2021-07-02 | Code |
| 7 | UDP-Pose-PSA(256x192) | 93.6 | No | Polarized Self-Attention: Towards High-quality P... | 2021-07-02 | Code |
| 8 | SCIO (HRNet-48) | 93.5 | No | Self-Constrained Inference Optimization on Struc... | 2022-07-06 | - |
| 9 | MSPN | 93.4 | No | Rethinking on Multi-Stage Networks for Human Pos... | 2019-01-01 | Code |
| 10 | MSPN | 93.4 | No | Rethinking on Multi-Stage Networks for Human Pos... | 2019-01-01 | Code |
| 11 | HRNet-W48 + extra data | 92.7 | No | Deep High-Resolution Representation Learning for... | 2019-02-25 | Code |
| 12 | HRNet-W48+UDP | 92.7 | No | The Devil is in the Details: Delving into Unbias... | 2019-11-18 | Code |
| 13 | HRFormer-B | 92.7 | No | HRFormer: High-Resolution Transformer for Dense ... | 2021-10-18 | Code |
| 14 | HRNet* | 92.7 | No | Deep High-Resolution Representation Learning for... | 2019-02-25 | Code |
| 15 | HRNet-W48+DARK | 92.6 | No | Distribution-Aware Coordinate Representation for... | 2019-10-14 | Code |
| 16 | OmniPose (WASPv2) | 92.6 | No | OmniPose: A Multi-Scale Framework for Multi-Pers... | 2021-03-18 | Code |
| 17 | EvoPose2D-L | 92.5 | No | EvoPose2D: Pushing the Boundaries of 2D Human Po... | 2020-11-17 | Code |
| 18 | HRNet | 92.5 | No | Deep High-Resolution Representation Learning for... | 2019-02-25 | Code |
| 19 | MIPNet | 92.4 | No | Multi-Instance Pose Networks: Rethinking Top-Dow... | 2021-01-27 | Code |
| 20 | Simple Base+* | 92.4 | No | Simple Baselines for Human Pose Estimation and T... | 2018-04-17 | Code |
| 21 | TransPose-H-A6 | 92.2 | No | TransPose: Keypoint Localization via Transformer | 2020-12-28 | Code |
| 22 | PoseBH-H | 91.9 | Yes | PoseBH: Prototypical Multi-Dataset Training Beyo... | 2025-05-23 | Code |
| 23 | DPIT-L | 91.9 | No | DPIT: Dual-Pipeline Integrated Transformer for H... | 2022-09-02 | - |
| 24 | Flow-based (ResNet-152) | 91.9 | No | Simple Baselines for Human Pose Estimation and T... | 2018-04-17 | Code |
| 25 | Simple Base | 91.9 | No | Simple Baselines for Human Pose Estimation and T... | 2018-04-17 | Code |
| 26 | S-ViPNAS-HRNetW32 | 91.7 | No | ViPNAS: Efficient Video Pose Estimation via Neur... | 2021-05-21 | Code |
| 27 | CPN+ [6, 9] | 91.7 | No | Cascaded Pyramid Network for Multi-Person Pose E... | 2017-11-20 | Code |
| 28 | CPN+ | 91.7 | No | Cascaded Pyramid Network for Multi-Person Pose E... | 2017-11-20 | Code |
| 29 | CPN | 91.4 | No | Cascaded Pyramid Network for Multi-Person Pose E... | 2017-11-20 | Code |
| 30 | CPN | 91.4 | No | Cascaded Pyramid Network for Multi-Person Pose E... | 2017-11-20 | Code |
| 31 | PoseFix | 91.2 | No | PoseFix: Model-agnostic General Human Pose Refin... | 2018-12-10 | Code |
| 32 | KAPAO-L | 91.2 | No | Rethinking Keypoint Representations: Modeling Ke... | 2021-11-16 | Code |
| 33 | TFPose (ND=6 ResNet-50) | 90.9 | No | TFPose: Direct Human Pose Estimation with Transf... | 2021-03-29 | - |
| 34 | Dite-HRNet-30 | 90.8 | No | Dite-HRNet: Dynamic Lightweight High-Resolution ... | 2022-04-22 | Code |
| 35 | S-ViPNAS-Res50 | 90.7 | No | ViPNAS: Efficient Video Pose Estimation via Neur... | 2021-05-21 | Code |
| 36 | Lite-HRNet-30 | 90.7 | Yes | Lite-HRNet: A Lightweight High-Resolution Network | 2021-04-13 | Code |
| 37 | KAPAO-M | 90.5 | No | Rethinking Keypoint Representations: Modeling Ke... | 2021-11-16 | Code |
| 38 | PPE (ResNeXt-101) | 90.3 | No | Deep Multi-Task Networks For Occluded Pedestrian... | 2022-06-15 | - |
| 39 | yolopose | 90.3 | No | YOLO-Pose: Enhancing YOLO for Multi Person Pose ... | 2022-04-14 | Code |
| 40 | HigherHRNet (ScaleNet_P4) | 90.3 | No | ScaleNAS: One-Shot Learning of Scale-Aware Repre... | 2020-11-30 | - |
| 41 | SMPR (HR-Net-32) | 89.7 | No | SMPR: Single-Stage Multi-Person Pose Regression | 2020-06-28 | Code |
| 42 | Lite-HRNet-18 | 89.4 | No | Lite-HRNet: A Lightweight High-Resolution Network | 2021-04-13 | Code |
| 43 | HigherHRNet (HR-Net-48) | 89.3 | No | HigherHRNet: Scale-Aware Representation Learning... | 2019-08-27 | Code |
| 44 | RMPE++ | 89.2 | No | RMPE: Regional Multi-person Pose Estimation | 2016-12-01 | Code |
| 45 | PersonLab | 89 | No | PersonLab: Person Pose Estimation and Instance S... | 2018-03-22 | Code |
| 46 | SPM | 88.5 | No | Single-Stage Multi-Person Pose Machines | 2019-08-24 | Code |
| 47 | KAPAO-S | 88.4 | No | Rethinking Keypoint Representations: Modeling Ke... | 2021-11-16 | Code |
| 48 | DirectPose (ResNet-101) | 87.8 | No | DirectPose: Direct End-to-End Multi-Person Pose ... | 2019-11-18 | Code |
| 49 | Mask-RCNN | 87.3 | No | Mask R-CNN | 2017-03-20 | Code |
| 50 | Mask R-CNN | 87.3 | No | Mask R-CNN | 2017-03-20 | Code |
| 51 | AE | 86.8 | No | Associative Embedding: End-to-End Learning for J... | 2016-11-16 | Code |
| 52 | DirectPose (ResNet-101) | 86.7 | No | DirectPose: Direct End-to-End Multi-Person Pose ... | 2019-11-18 | Code |
| 53 | OpenPose | 86.2 | Yes | OpenPose: Realtime Multi-Person 2D Pose Estimati... | 2018-12-18 | Code |
| 54 | Faster R-CNN (ImageNet+300M) | 85.7 | Yes | Revisiting Unreasonable Effectiveness of Data in... | 2017-07-10 | Code |
| 55 | G-RMI | 85.5 | No | Towards Accurate Multi-person Pose Estimation in... | 2017-01-06 | - |
| 56 | G-RMI | 85.5 | No | Towards Accurate Multi-person Pose Estimation in... | 2017-01-06 | - |
| 57 | G-RMI | 85.5 | No | Towards Accurate Multi-person Pose Estimation in... | 2017-01-06 | - |
| 58 | CMU-Pose | 84.9 | No | Realtime Multi-Person 2D Pose Estimation using P... | 2016-11-24 | Code |
| 59 | CMU Pose | 84.9 | No | Realtime Multi-Person 2D Pose Estimation using P... | 2016-11-24 | Code |
| 60 | CMU-Pose | 84.9 | No | Realtime Multi-Person 2D Pose Estimation using P... | 2016-11-24 | Code |
| 61 | RMPE | 83.7 | No | RMPE: Regional Multi-person Pose Estimation | 2016-12-01 | Code |
| 62 | RMPE | 83.7 | No | RMPE: Regional Multi-person Pose Estimation | 2016-12-01 | Code |
| 63 | Plain-DETR (Swin-L) | 82.1 | No | - | - | Code |
| 64 | EVA | 81.9 | No | EVA: Exploring the Limits of Masked Visual Repre... | 2022-11-14 | Code |
| 65 | Group DETR v2 | 81.8 | No | Group DETR v2: Strong Object Detector with Encod... | 2022-11-07 | - |
| 66 | Focal-Stable-DINO (Focal-Huge, no TTA) | 81.7 | No | A Strong and Reproducible Object Detector with O... | 2023-04-25 | Code |
| 67 | Relation-DETR (Focal-L) | 80.8 | No | Relation DETR: Exploring Explicit Position Relat... | 2024-07-16 | Code |
| 68 | DETA (Swin-L) | 80.4 | No | NMS Strikes Back | 2022-12-12 | Code |
| 69 | GLIP (Swin-L, multi-scale) | 79.5 | No | Grounded Language-Image Pre-training | 2021-12-07 | Code |
| 70 | PIIP-H6B (DINO) | 79 | No | Parameter-Inverted Image Pyramid Networks | 2024-06-06 | Code |
| 71 | DyHead (Swin-L, multi scale, self-training) | 78.5 | No | Dynamic Head: Unifying Object Detection Heads wi... | 2021-06-15 | Code |
| 72 | DyHead (Swin-L, multi scale) | 77.1 | No | Dynamic Head: Unifying Object Detection Heads wi... | 2021-06-15 | Code |
| 73 | QueryInst (single-scale) | 75.9 | No | Instances as Queries | 2021-05-05 | Code |
| 74 | SOLQ (Swin-L, single scale) | 74.6 | No | SOLQ: Segmenting Objects by Learning Queries | 2021-06-04 | Code |
| 75 | DetectoRS (ResNeXt-101-64x4d, multi-scale) | 74.2 | No | DetectoRS: Detecting Objects with Recursive Feat... | 2020-06-03 | Code |
| 76 | CenterNet2 (Res2Net-101-DCN-BiFPN, self-training, 1560 single-scale) | 74 | No | Probabilistic two-stage detection | 2021-03-12 | Code |
| 77 | PyCenterNet (Swin-L, multi-scale) | 73.7 | No | CenterNet++ for Object Detection | 2022-04-18 | Code |
| 78 | DetectoRS (ResNeXt-101-32x4d, multi-scale) | 73.5 | No | DetectoRS: Detecting Objects with Recursive Feat... | 2020-06-03 | Code |
| 79 | YOLOR-D6 (1280, single-scale, 30 fps) | 73.3 | No | You Only Learn One Representation: Unified Netwo... | 2021-05-10 | Code |
| 80 | YOLOv4-P7 with TTA | 73.2 | No | Scaled-YOLOv4: Scaling Cross Stage Partial Network | 2020-11-16 | Code |
| 81 | YOLOv4-P6 with TTA | 72.6 | No | Scaled-YOLOv4: Scaling Cross Stage Partial Network | 2020-11-16 | Code |
| 82 | YOLOv4-P6 CSP-P6 (single-scale, 32 fps) | 72.3 | No | Scaled-YOLOv4: Scaling Cross Stage Partial Network | 2020-11-16 | Code |
| 83 | DyHead (ResNeXt-64x4d-101-DCN, multi scale) | 72.1 | No | Dynamic Head: Unifying Object Detection Heads wi... | 2021-06-15 | Code |
| 84 | ResNeSt-200 (multi-scale) | 72 | No | ResNeSt: Split-Attention Networks | 2020-04-19 | Code |
| 85 | Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) | 71.9 | No | CBNet: A Novel Composite Backbone Network Archit... | 2019-09-09 | Code |
| 86 | Deformable DETR (ResNeXt-101+DCN) | 71.9 | No | Deformable DETR: Deformable Transformers for End... | 2020-10-08 | Code |
| 87 | TSD(SENet154-DCN,multi-scale) | 71.9 | No | Revisiting the Sibling Head in Object Detector | 2020-03-17 | Code |
| 88 | RetinaNet (SpineNet-190, 1280x1280) | 71.8 | No | SpineNet: Learning Scale-Permuted Backbone for R... | 2019-12-10 | Code |
| 89 | UniverseNet-20.08d (Res2Net-101, DCN, multi-scale) | 71.6 | No | USB: Universal-Scale Object Detection Benchmark | 2021-03-25 | Code |
| 90 | PAA (ResNext-152-32x8d + DCN, multi-scale) | 71.6 | No | Probabilistic Anchor Assignment with IoU Predict... | 2020-07-16 | Code |
| 91 | DetectoRS (ResNeXt-101-32x4d, single-scale) | 71.6 | No | DetectoRS: Detecting Objects with Recursive Feat... | 2020-06-03 | Code |
| 92 | EfficientDet-D7 (1536) | 71.6 | Yes | EfficientDet: Scalable and Efficient Object Dete... | 2019-11-20 | Code |
| 93 | LSNet (Res2Net-101+ DCN, multi-scale) | 71.1 | No | Location-Sensitive Visual Recognition with Cross... | 2021-04-11 | Code |
| 94 | GFLV2 (Res2Net-101, DCN, multiscale) | 70.9 | No | Generalized Focal Loss V2: Learning Reliable Loc... | 2020-11-25 | Code |
| 95 | GCNet (ResNeXt-101 + DCN + cascade + GC r4) | 70.9 | No | Global Context Networks | 2020-12-24 | Code |
| 96 | AC-FPN Cascade R-CNN (X-152-32x8d-FPN-IN5k, multi scale, only CEM) | 70.4 | No | Attention-guided Context Feature Pyramid Network... | 2020-05-23 | Code |
| 97 | RetinaNet (SpineNet-143, 1280x1280) | 70.4 | No | SpineNet: Learning Scale-Permuted Backbone for R... | 2019-12-10 | Code |
| 98 | YOLOv4-P5 with TTA | 70.3 | No | Scaled-YOLOv4: Scaling Cross Stage Partial Network | 2020-11-16 | Code |
| 99 | aLRP Loss (ResNext-101-64x4d, DCN, multiscale test) | 70.3 | No | A Ranking-based, Balanced Loss Function Unifying... | 2020-09-28 | Code |
| 100 | RepPoints v2 (ResNeXt-101, DCN, multi-scale) | 70.1 | No | RepPoints V2: Verification Meets Regression for ... | 2020-07-16 | Code |
| 101 | UniverseNet-20.08d (Res2Net-101, DCN, single-scale) | 70 | No | USB: Universal-Scale Object Detection Benchmark | 2021-03-25 | Code |
| 102 | PP-YOLOE-x(CSPRepResNet-x, 640x640, single-scale ) | 69.9 | No | PP-YOLOE: An evolved version of YOLO | 2022-03-30 | Code |
| 103 | FreeAnchor + SEPC (DCN, ResNext-101-64x4d) | 69.8 | No | Scale-Equalizing Pyramid Convolution for Object ... | 2020-05-06 | Code |
| 104 | TridentNet (ResNet-101-Deformable, Image Pyramid) | 69.7 | No | Scale-Aware Trident Networks for Object Detection | 2019-01-07 | Code |
| 105 | YOLOX-X (Modified CSP v5) | 69.6 | No | YOLOX: Exceeding YOLO Series in 2021 | 2021-07-18 | Code |
| 106 | TSD(ResNet-101-Deformable, Image Pyramid) | 69.6 | No | Revisiting the Sibling Head in Object Detector | 2020-03-17 | Code |
| 107 | DAT-S (RetinaNet) | 69.6 | No | Vision Transformer with Deformable Attention | 2022-01-03 | Code |
| 108 | D2Det (ResNet-101-DCN, multi-scale test) | 69.4 | No | - | - | Code |
| 109 | aLRP Loss (ResNext-101-64x4d, DCN, single scale) | 69.3 | No | A Ranking-based, Balanced Loss Function Unifying... | 2020-09-28 | Code |
| 110 | GFLV2 (Res2Net-101, DCN) | 69 | No | Generalized Focal Loss V2: Learning Reliable Loc... | 2020-11-25 | Code |
| 111 | PP-YOLOE-l(CSPRepResNet-l, 640x640, single-scale ) | 68.9 | No | PP-YOLOE: An evolved version of YOLO | 2022-03-30 | Code |
| 112 | ATSS (ResNetXt-64x4d-101+DCN,multi-scale) | 68.9 | No | Bridging the Gap Between Anchor-based and Anchor... | 2019-12-05 | Code |
| 113 | RepPoints v2 (ResNeXt-101, DCN) | 68.9 | No | RepPoints V2: Verification Meets Regression for ... | 2020-07-16 | Code |
| 114 | OTA (ResNeXt-101+DCN, multiscale) | 68.6 | No | OTA: Optimal Transport Assignment for Object Det... | 2021-03-26 | Code |
| 115 | RetinaNet (SpineNet-96, 1024x1024) | 68.4 | No | SpineNet: Learning Scale-Permuted Backbone for R... | 2019-12-10 | Code |
| 116 | aLRP Loss (ResNext-101-64x4d, single scale) | 68.4 | No | A Ranking-based, Balanced Loss Function Unifying... | 2020-09-28 | Code |
| 117 | Dynamic R-CNN (ResNet-101-DCN, multi-scale) | 68.3 | No | Dynamic R-CNN: Towards High Quality Object Detec... | 2020-04-13 | Code |
| 118 | DCNv2 (ResNet-101, multi-scale) | 67.9 | No | Deformable ConvNets v2: More Deformable, Better ... | 2018-11-27 | Code |
| 119 | GFLV2 (ResNeXt-101, 32x4d, DCN) | 67.6 | No | Generalized Focal Loss V2: Learning Reliable Loc... | 2020-11-25 | Code |
| 120 | GCNet (ResNeXt-101 + DCN + cascade + GC r4) | 67.6 | No | GCNet: Non-local Networks Meet Squeeze-Excitatio... | 2019-04-25 | Code |
| 121 | UniverseNet-20.08 (Res2Net-50, DCN, single-scale) | 67.5 | No | USB: Universal-Scale Object Detection Benchmark | 2021-03-25 | Code |
| 122 | InterNet (ResNet-101-FPN, multi-scale) | 67.5 | No | Feature Intertwiner for Object Detection | 2019-03-28 | Code |
| 123 | GFL (X-101-32x4d-DCN, single-scale) | 67.4 | No | Generalized Focal Loss: Learning Qualified and D... | 2020-06-08 | Code |
| 124 | SAPD (ResNeXt-101, single-scale) | 67.4 | No | Soft Anchor-Point Object Detection | 2019-11-27 | Code |
| 125 | RPDet (ResNet-101-DCN, multi-scale) | 67.4 | No | RepPoints: Point Set Representation for Object D... | 2019-04-25 | Code |
| 126 | CPNDet (Hourglass-104, multi-scale) | 67.3 | No | Corner Proposal Network for Anchor-free, Two-sta... | 2020-07-27 | Code |
| 127 | D-RFCN + SNIP (DPN-98 with flip, multi-scale) | 67.3 | No | An Analysis of Scale Invariance in Object Detect... | 2017-11-22 | - |
| 128 | PANet (ResNeXt-101, multi-scale) | 67.2 | No | Path Aggregation Network for Instance Segmentation | 2018-03-05 | Code |
| 129 | SNIPER (ResNet-101) | 67 | No | SNIPER: Efficient Multi-Scale Training | 2018-05-23 | Code |
| 130 | PP-YOLOE-m(CSPRepResNet-m, 640x640, single-scale ) | 66.5 | No | PP-YOLOE: An evolved version of YOLO | 2022-03-30 | Code |
| 131 | GFLV2 (ResNet-101-DCN) | 66.5 | No | Generalized Focal Loss V2: Learning Reliable Loc... | 2020-11-25 | Code |
| 132 | RetinaNet (SpineNet-49, 896x896) | 66.3 | No | SpineNet: Learning Scale-Permuted Backbone for R... | 2019-12-10 | Code |
| 133 | MatrixNet Corners (ResNet-152, multi-scale) | 66.2 | No | Matrix Nets: A New Deep Architecture for Object ... | 2019-08-13 | Code |
| 134 | HTC (HRNetV2p-W48) | 65.9 | No | Deep High-Resolution Representation Learning for... | 2019-08-20 | Code |
| 135 | DyHead (ResNeXt-64x4d-101) | 65.7 | No | Dynamic Head: Unifying Object Detection Heads wi... | 2021-06-15 | Code |
| 136 | Faster R-CNN (LIP-ResNet-101-MD w FPN) | 65.7 | No | LIP: Local Importance-based Pooling | 2019-08-12 | Code |
| 137 | YOLOv4-608 | 65.7 | Yes | YOLOv4: Optimal Speed and Accuracy of Object Det... | 2020-04-23 | Code |
| 138 | D-RFCN + SNIP (ResNet-101, multi-scale) | 65.5 | No | An Analysis of Scale Invariance in Object Detect... | 2017-11-22 | - |
| 139 | FSAF (ResNeXt-101, multi-scale) | 65.2 | No | Feature Selective Anchor-Free Module for Single-... | 2019-03-02 | Code |
| 140 | HoughNet (MS) | 65.1 | No | HoughNet: Integrating near and long-range eviden... | 2020-07-05 | Code |
| 141 | aLRP Loss (ResNext-101, DCN, 500 scale) | 65 | No | A Ranking-based, Balanced Loss Function Unifying... | 2020-09-28 | Code |
| 142 | SNIPER (ResNet-50) | 65 | No | SNIPER: Efficient Multi-Scale Training | 2018-05-23 | Code |
| 143 | RPDet (ResNet-101-DCN) | 65 | No | RepPoints: Point Set Representation for Object D... | 2019-04-25 | Code |
| 144 | PPDet (ResNeXt-101-FPN, multiscale) | 64.8 | No | Reducing Label Noise in Anchor-Free Object Detec... | 2020-08-03 | Code |
| 145 | M2Det (VGG-16, multi-scale) | 64.6 | No | M2Det: A Single-Shot Object Detector based on Mu... | 2018-11-12 | Code |
| 146 | CenterNet511 (Hourglass-104, multi-scale) | 64.5 | No | CenterNet: Keypoint Triplets for Object Detection | 2019-04-17 | Code |
| 147 | CenterMask+VoVNetV2-99 (single-scale) | 64.5 | No | CenterMask : Real-Time Anchor-Free Instance Segm... | 2019-11-15 | Code |
| 148 | AC-FPN Cascade R-CNN(ResNet-101, single scale) | 64.4 | No | Attention-guided Context Feature Pyramid Network... | 2020-05-23 | Code |
| 149 | M2Det (ResNet-101, multi-scale) | 64.4 | No | M2Det: A Single-Shot Object Detector based on Mu... | 2018-11-12 | Code |
| 150 | GFLV2 (ResNet-101) | 64.3 | No | Generalized Focal Loss V2: Learning Reliable Loc... | 2020-11-25 | Code |
| 151 | FreeAnchor (ResNeXt-101) | 64.3 | No | FreeAnchor: Learning to Match Anchors for Visual... | 2019-09-05 | Code |
| 152 | Cascade R-CNN-FPN (ResNet-101, map-guided) | 64.2 | No | InstaBoost: Boosting Instance Segmentation via P... | 2019-08-21 | Code |
| 153 | YOLOv4 (CD53) | 64.1 | Yes | Scaled-YOLOv4: Scaling Cross Stage Partial Network | 2020-11-16 | Code |
| 154 | FCOS (ResNeXt-64x4d-101-FPN 4 + improvements) | 64.1 | No | FCOS: Fully Convolutional One-Stage Object Detec... | 2019-04-02 | Code |
| 155 | YOLOv3 @800 + ASFF* (Darknet-53) | 64.1 | Yes | Learning Spatial Fusion for Single-Shot Object D... | 2019-11-21 | Code |
| 156 | Mask R-CNN (HRNetV2p-W48 + cascade) | 64 | No | Deep High-Resolution Representation Learning for... | 2019-08-20 | Code |
| 157 | Libra R-CNN (ResNeXt-101-FPN) | 64 | No | Libra R-CNN: Towards Balanced Learning for Objec... | 2019-04-04 | Code |
| 158 | HTC (ResNeXt-101-FPN) | 63.9 | No | Hybrid Task Cascade for Instance Segmentation | 2019-01-22 | Code |
| 159 | RetinaNet (SpineNet-49, 640x640) | 63.8 | No | SpineNet: Learning Scale-Permuted Backbone for R... | 2019-12-10 | Code |
| 160 | TridentNet (ResNet-101) | 63.6 | No | Scale-Aware Trident Networks for Object Detection | 2019-01-07 | Code |
| 161 | Faster R-CNN (HRNetV2p-W48) | 63.6 | No | Deep High-Resolution Representation Learning for... | 2019-08-20 | Code |
| 162 | FoveaBox (ResNeXt-101) | 63.5 | No | FoveaBox: Beyond Anchor-based Object Detector | 2019-04-08 | Code |
| 163 | CenterMask + X-101-32x8d (single-scale) | 63.4 | No | CenterMask : Real-Time Anchor-Free Instance Segm... | 2019-11-15 | Code |
| 164 | CenterMask+VoVNet2-57 (single-scale) | 63.1 | No | CenterMask : Real-Time Anchor-Free Instance Segm... | 2019-11-15 | Code |
| 165 | Grid R-CNN (ResNeXt-101-FPN) | 63 | No | Grid R-CNN | 2018-11-29 | Code |
| 166 | YOLOF-DC5 | 62.9 | No | You Only Look One-level Feature | 2021-03-17 | Code |
| 167 | RefineDet512+ (ResNet-101) | 62.9 | No | Single-Shot Refinement Neural Network for Object... | 2017-11-18 | Code |
| 168 | RPDet (ResNet-101) | 62.9 | No | RepPoints: Point Set Representation for Object D... | 2019-04-25 | Code |
| 169 | FCOS (ResNeXt-101-64x4d-FPN) | 62.8 | No | FCOS: Fully Convolutional One-Stage Object Detec... | 2019-04-02 | Code |
| 170 | GHM-C + GHM-R (RetinaNet-FPN-ResNeXt-101) | 62.8 | No | Gradient Harmonized Single-stage Detector | 2018-11-13 | Code |
| 171 | RetinaMask (ResNeXt-101-FPN-GN) | 62.5 | No | RetinaMask: Learning to predict masks improves s... | 2019-01-10 | Code |
| 172 | GFLV2 (ResNet-50) | 62.3 | No | Generalized Focal Loss V2: Learning Reliable Loc... | 2020-11-25 | Code |
| 173 | SpineNet-49 (640, RetinaNet, single-scale) | 62.3 | No | SpineNet: Learning Scale-Permuted Backbone for R... | 2019-12-10 | Code |
| 174 | Mask R-CNN (ResNeXt-101-FPN) | 62.3 | No | Mask R-CNN | 2017-03-20 | Code |
| 175 | FCOS (ResNeXt-32x8d-101-FPN) | 62.2 | No | FCOS: Fully Convolutional One-Stage Object Detec... | 2019-04-02 | Code |
| 176 | Cascade R-CNN (ResNet-101-FPN+, cascade) | 62.1 | No | Cascade R-CNN: Delving into High Quality Object ... | 2017-12-03 | Code |
| 177 | Cascade R-CNN | 62.1 | No | Cascade R-CNN: High Quality Object Detection and... | 2019-06-24 | Code |
| 178 | FSAF (ResNet-101, single-scale) | 61.5 | No | Feature Selective Anchor-Free Module for Single-... | 2019-03-02 | Code |
| 179 | HSD (Rest101, 768x768, single-scale test) | 61.2 | No | - | - | Code |
| 180 | RetinaNet (ResNeXt-101-FPN) | 61.1 | No | Focal Loss for Dense Object Detection | 2017-08-07 | Code |
| 181 | Cascade R-CNN (ResNet-101-FPN+) | 61.1 | No | Cascade R-CNN: Delving into High Quality Object ... | 2017-12-03 | Code |
| 182 | DyHead (ResNet-50) | 60.7 | No | Dynamic Head: Unifying Object Detection Heads wi... | 2021-06-15 | Code |
| 183 | ExtremeNet (Hourglass-104, multi-scale) | 60.5 | No | Bottom-up Object Detection by Grouping Extreme a... | 2019-01-23 | Code |
| 184 | PP-YOLOE-s(CSPRepResNet-s, 640x640, single-scale ) | 60.5 | No | PP-YOLOE: An evolved version of YOLO | 2022-03-30 | Code |
| 185 | RetinaNet (SpineNet-49S, 640x640) | 60.5 | No | SpineNet: Learning Scale-Permuted Backbone for R... | 2019-12-10 | Code |
| 186 | Mask R-CNN (ResNet-101-FPN, CBN) | 60.5 | No | Cross-Iteration Batch Normalization | 2020-02-13 | Code |
| 187 | FCOS (HRNet-W32-5l) | 60.4 | No | FCOS: Fully Convolutional One-Stage Object Detec... | 2019-04-02 | Code |
| 188 | TAL + TAP | 60.3 | No | TOOD: Task-aligned One-stage Object Detection | 2021-08-17 | Code |
| 189 | Mask R-CNN (ResNet-101-FPN) | 60.3 | No | Mask R-CNN | 2017-03-20 | Code |
| 190 | RDSNet (ResNet-101, RetinaNet, mask, MBRM) | 60.1 | No | RDSNet: A New Deep Architecture for Reciprocal O... | 2019-12-11 | Code |
| 191 | Cascade R-CNN (ResNet-50-FPN+, cascade) | 59.9 | No | Cascade R-CNN: Delving into High Quality Object ... | 2017-12-03 | Code |
| 192 | M2Det (VGG-16, single-scale) | 59.7 | No | M2Det: A Single-Shot Object Detector based on Mu... | 2018-11-12 | Code |
| 193 | Fast R-CNN (Cascade RPN) | 59.4 | Yes | Cascade RPN: Delving into High-Quality Region Pr... | 2019-09-15 | Code |
| 194 | M2Det (ResNet-101, single-scale) | 59.4 | No | M2Det: A Single-Shot Object Detector based on Mu... | 2018-11-12 | Code |
| 195 | FCOS (HRNetV2p-W48) | 59.3 | Yes | Deep High-Resolution Representation Learning for... | 2019-08-20 | Code |
| 196 | GA-Faster-RCNN | 59.2 | No | Region Proposal by Guided Anchoring | 2019-01-10 | Code |
| 197 | RetinaNet (ResNet-101-FPN) | 59.1 | No | Focal Loss for Dense Object Detection | 2017-08-07 | Code |
| 198 | Cascade R-CNN (ResNet-50-FPN+) | 59 | No | Cascade R-CNN: Delving into High Quality Object ... | 2017-12-03 | Code |
| 199 | Faster R-CNN (Cascade RPN) | 58.9 | Yes | Cascade RPN: Delving into High-Quality Region Pr... | 2019-09-15 | Code |
| 200 | RefineDet512+ (VGG-16) | 58.7 | No | Single-Shot Refinement Neural Network for Object... | 2017-11-18 | Code |
| 201 | RetinaMask (ResNet-50-FPN) | 58.6 | No | RetinaMask: Learning to predict masks improves s... | 2019-01-10 | Code |
| 202 | DeformConv-R-FCN (Aligned-Inception-ResNet) | 58 | No | Deformable Convolutional Networks | 2017-03-17 | Code |
| 203 | Faster R-CNN (ImageNet+300M) | 58 | No | Revisiting Unreasonable Effectiveness of Data in... | 2017-07-10 | Code |
| 204 | CornerNet511 (Hourglass-104, multi-scale) | 57.8 | No | CornerNet: Detecting Objects as Paired Keypoints | 2018-08-03 | Code |
| 205 | RefineDet512 (ResNet-101) | 57.5 | No | Single-Shot Refinement Neural Network for Object... | 2017-11-18 | Code |
| 206 | SaccadeNet (DLA-34-DCN) | 55.6 | No | SaccadeNet: A Fast and Accurate Object Detector | 2020-03-26 | Code |
| 207 | ExtremeNet (Hourglass-104, single-scale) | 55.5 | No | Bottom-up Object Detection by Grouping Extreme a... | 2019-01-23 | Code |
| 208 | CornerNet511 (Hourglass-52, single-scale) | 53.7 | No | CornerNet: Detecting Objects as Paired Keypoints | 2018-08-03 | Code |
| 209 | wetectron(single-model, VGG16) | 24.8 | No | Instance-aware, Context-focused, and Memory-effi... | 2020-04-09 | Code |
| 210 | WSGARN+SSD | 13.6 | No | Weakly Supervised Object Discovery by Generative... | 2017-11-22 | - |
| 211 | WCCN | 12.3 | No | Weakly Supervised Cascaded Convolutional Networks | 2016-11-24 | - |
| 212 | WSDDN | 11.5 | No | Weakly Supervised Deep Detection Networks | 2015-11-09 | Code |
| 213 | PCT (256x256) | 9 | No | Human Pose as Compositional Tokens | 2023-03-21 | Code |