Object Detection On Coco O

评估指标

Average mAP
Effective Robustness

评测结果

各个模型在此基准测试上的表现结果

模型名称
Average mAP
Effective Robustness
Paper TitleRepository
SSD (VGG-16)13.60.36SSD: Single Shot MultiBox Detector-
GRiT (ViT-H)42.915.72GRiT: A Generative Region-to-text Transformer for Object Understanding-
UniverseNet (R2-101-DCN)-1.86USB: Universal-Scale Object Detection Benchmark-
FIBER-B (Swin-B)33.711.43Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone-
DyHead (ResNet-50)19.30.16Dynamic Head: Unifying Object Detection Heads with Attentions-
Mask R-CNN (ResNet-50)17.1-Mask R-CNN-
VFNet (RX-101-64x4d)28.05.27VarifocalNet: An IoU-aware Dense Object Detector-
DETA (Swin-L)48.520.15NMS Strikes Back-
Mask R-CNN (ResNet-50)--0.11Mask R-CNN-
GCNet (RX-101-32x4d-DCN)26.04.38GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond-
RetinaNet (ResNet-50)16.60.18Focal Loss for Dense Object Detection-
YOLOv7-E6E32.06.42YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors-
YOLOX-X30.37.26YOLOX: Exceeding YOLO Series in 2021-
DINO (Swin-L)42.115.76DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection-
GLIP-L (Swin-L)48.024.89Grounded Language-Image Pre-training-
YOLOX-S20.62.48YOLOX: Exceeding YOLO Series in 2021-
YOLOS-B (ViT-B)20.01.05You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection-
DyHead (Swin-L)35.310.00Dynamic Head: Unifying Object Detection Heads with Attentions-
YOLOv3 (DarkNet-53)14.8-0.37YOLOv3: An Incremental Improvement-
RepPointsV2 (RX-101-64x4d-DCN)24.92.7RepPoints V2: Verification Meets Regression for Object Detection-
0 of 45 row(s) selected.