Object Detection On Coco O

Metrics

Average mAP

Effective Robustness

Results

Performance results of various models on this benchmark

			Paper Title
EVA	57.8	28.86	EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
DETA (Swin-L)	48.5	20.15	NMS Strikes Back
GLIP-L (Swin-L)	48.0	24.89	Grounded Language-Image Pre-training
GRiT (ViT-H)	42.9	15.72	GRiT: A Generative Region-to-text Transformer for Object Understanding
DINO (Swin-L)	42.1	15.76	DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
CBNetV2 (Swin-L)	39.0	12.36	CBNet: A Composite Backbone Network Architecture for Object Detection
ConvNeXt-XL (Cascade Mask R-CNN)	37.5	12.68	A ConvNet for the 2020s
InternImage-L (Cascade Mask R-CNN)	37.0	11.72	InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
DyHead (Swin-L)	35.3	10.00	Dynamic Head: Unifying Object Detection Heads with Attentions
ViTDet (ViT-H)	34.3	-	Exploring Plain Vision Transformer Backbones for Object Detection
ViT-Adapter (BEiTv2-L)	34.25	7.79	Vision Transformer Adapter for Dense Predictions
FIBER-B (Swin-B)	33.7	11.43	Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone
QueryInst (Swin-L)	33.2	8.26	Instances as Queries
YOLOv6-L6	32.5	6.73	YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
YOLOv7-E6E	32.0	6.42	YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
MViTV2-H (Cascade Mask R-CNN)	30.9	5.62	MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
Det-AdvProp (EfficientNet-B5)	30.8	7.34	Robust and Accurate Object Detection via Adversarial Learning
YOLOv4-P6	30.4	5.89	YOLOv4: Optimal Speed and Accuracy of Object Detection
YOLOX-X	30.3	7.26	YOLOX: Exceeding YOLO Series in 2021
CenterNet2 (R2-101-DCN)	29.5	4.29	Probabilistic two-stage detection

0 of 45 row(s) selected.

Command Palette

Object Detection On Coco O

Metrics

Results