| Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation | ✓ Link | 89.3% | | | | | Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale) | 2020-12-13 |
| YOLO-Former: YOLO Shakes Hand With ViT | | 86.01% | | | | | YOLO-Former | 2024-01-11 |
| Class-agnostic Object Detection with Multi-modal Transformer | ✓ Link | 84.16% | 84.16 | | | | DETReg (MDef-DETR) | 2021-11-22 |
| Hierarchical Shot Detector | ✓ Link | 83.0% | | | | | HSD (VGG16, 512x512, single-scale test) | 2019-10-01 |
| CoupleNet: Coupling Global Structure with Local Parts for Object Detection | ✓ Link | 82.7% | | | | | CoupleNet | 2017-08-09 |
| EEEA-Net: An Early Exit Evolutionary Neural Architecture Search | ✓ Link | 81.8% | | | | | EEEA-Net-C2 (YOLOv4) | 2021-08-13 |
| Hierarchical Shot Detector | ✓ Link | 81.7% | | | | | HSD (VGG16, 320x320, single-scale test) | 2019-10-01 |
| SSD: Single Shot MultiBox Detector | ✓ Link | 81.6% | | | | | SSD512 (07+12+COCO) | 2015-12-08 |
| BlitzNet: A Real-Time Deep Network for Scene Understanding | ✓ Link | 81.5% | | | | | BlitzNet512 + seg (s8) | 2017-08-09 |
| Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection | ✓ Link | 81.5% | | | | | Localize | 2020-09-29 |
| Objects as Points | ✓ Link | 80.7% | | | | | CenterNet(DLA34, Flip, 512x512) | 2019-04-16 |
| Self-Knowledge Distillation with Progressive Refinement of Targets | ✓ Link | 79.7% | | | | | PS-KD (ResNet-152, CutMix) | 2020-06-22 |
| DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention | ✓ Link | 79.2% | | | | | DPNet | 2022-09-28 |
| Training Region-based Object Detectors with Online Hard Example Mining | ✓ Link | 78.9% | | | | | OHEM | 2016-04-12 |
| YOLO9000: Better, Faster, Stronger | ✓ Link | 78.6% | | | | | YOLO v2 | 2016-12-25 |
| ThunderNet: Towards Real-time Generic Object Detection | ✓ Link | 78.6% | | | | | ThunderNet SNet535 Backbone | 2019-03-28 |
| DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling | ✓ Link | 77.1% | | | | | DeNet-101 (skip) | 2017-03-30 |
| Random Erasing Data Augmentation | ✓ Link | 76.2% | | | | | I+ORE | 2017-08-16 |
| Learning Visual Representations for Transfer Learning by Suppressing Texture | ✓ Link | 74.37% | | | | | Perona Malik (Perona and Malik, 1990) | 2020-11-03 |
| A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection | ✓ Link | 74.2% | | | | | FRCN | 2017-04-11 |
| Bounding Box Regression with Uncertainty for Accurate Object Detection | ✓ Link | 71.6% | | | | | VGG-16 + KL Loss + var voting + soft-NMS | 2018-09-23 |
| Fast R-CNN | ✓ Link | 70.0% | | | | | Fast R-CNN | 2015-04-30 |
| Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection | ✓ Link | 68.5% | | | | | subCNN | 2016-04-16 |
| You Only Look Once: Unified, Real-Time Object Detection | ✓ Link | 63.4% | | | | | YOLO | 2015-06-08 |
| Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition | ✓ Link | 60.9% | | | | | SPP(combination) | 2014-06-18 |
| Rich feature hierarchies for accurate object detection and semantic segmentation | ✓ Link | 58.5% | | | | | R-CNN | 2013-11-11 |
| Deformable Part Models are Convolutional Neural Networks | ✓ Link | 45.2% | | | | | Deformable Parts Model (DeepPyramid) | 2014-09-18 |
| Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO | ✓ Link | 42.3% | | | | | TinyissimoYOLO-v8 | 2023-11-02 |
| FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs | ✓ Link | 22.90% | 46.31 | | | | FemotoDet | 2023-01-17 |
| Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box | ✓ Link | | | 64.44 | 38.52 | | YOLOv7+Inner-IoU | 2023-11-06 |