Object Detection On Pascal Voc 2007

Métriques

MAP

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	MAP	Paper Title
CenterNet(DLA34, Flip, 512x512)	80.7%	Objects as Points
SPP(combination)	60.9%	Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Perona Malik (Perona and Malik, 1990)	74.37%	Learning Visual Representations for Transfer Learning by Suppressing Texture
YOLO v2	78.6%	YOLO9000: Better, Faster, Stronger
TinyissimoYOLO-v8	42.3%	Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO
OHEM	78.9%	Training Region-based Object Detectors with Online Hard Example Mining
ThunderNet SNet535 Backbone	78.6%	ThunderNet: Towards Real-time Generic Object Detection
HSD (VGG16, 512x512, single-scale test)	83.0%	Hierarchical Shot Detector
Deformable Parts Model (DeepPyramid)	45.2%	Deformable Part Models are Convolutional Neural Networks
I+ORE	76.2%	Random Erasing Data Augmentation
HSD (VGG16, 320x320, single-scale test)	81.7%	Hierarchical Shot Detector
YOLOv7+Inner-IoU	-	Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box
BlitzNet512 + seg (s8)	81.5%	BlitzNet: A Real-Time Deep Network for Scene Understanding
R-CNN	58.5%	Rich feature hierarchies for accurate object detection and semantic segmentation
SSD512 (07+12+COCO)	81.6%	SSD: Single Shot MultiBox Detector
DETReg (MDef-DETR)	84.16%	Class-agnostic Object Detection with Multi-modal Transformer
VGG-16 + KL Loss + var voting + soft-NMS	71.6%	Bounding Box Regression with Uncertainty for Accurate Object Detection
Fast R-CNN	70.0%	Fast R-CNN
FemotoDet	22.90%	FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs
PS-KD (ResNet-152, CutMix)	79.7%	Self-Knowledge Distillation with Progressive Refinement of Targets

0 of 30 row(s) selected.