Object Detection On Pascal Voc 2007

评估指标

MAP

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale)	89.3%	Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
YOLO-Former	86.01%	YOLO-Former: YOLO Shakes Hand With ViT	-
DETReg (MDef-DETR)	84.16%	Class-agnostic Object Detection with Multi-modal Transformer
HSD (VGG16, 512x512, single-scale test)	83.0%	Hierarchical Shot Detector	-
CoupleNet	82.7%	CoupleNet: Coupling Global Structure with Local Parts for Object Detection
EEEA-Net-C2 (YOLOv4)	81.8%	EEEA-Net: An Early Exit Evolutionary Neural Architecture Search
HSD (VGG16, 320x320, single-scale test)	81.7%	Hierarchical Shot Detector	-
SSD512 (07+12+COCO)	81.6%	SSD: Single Shot MultiBox Detector
BlitzNet512 + seg (s8)	81.5%	BlitzNet: A Real-Time Deep Network for Scene Understanding
Localize	81.5%	Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection
CenterNet(DLA34, Flip, 512x512)	80.7%	Objects as Points
PS-KD (ResNet-152, CutMix)	79.7%	Self-Knowledge Distillation with Progressive Refinement of Targets
DPNet	79.2%	DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention
OHEM	78.9%	Training Region-based Object Detectors with Online Hard Example Mining
YOLO v2	78.6%	YOLO9000: Better, Faster, Stronger
ThunderNet SNet535 Backbone	78.6%	ThunderNet: Towards Real-time Generic Object Detection
DeNet-101 (skip)	77.1%	DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling
I+ORE	76.2%	Random Erasing Data Augmentation
Perona Malik (Perona and Malik, 1990)	74.37%	Learning Visual Representations for Transfer Learning by Suppressing Texture
FRCN	74.2%	A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection

0 of 30 row(s) selected.