HyperAI超神经

首页资讯最新论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Cross Domain Few Shot Object Detection On 4

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

模型名称	mAP	Paper Title	Repository
FSCE	12.0	FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
DeFRCN	12.1	DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
Detic-FT	16.8	Detecting Twenty-thousand Classes using Image-level Supervision
TFA w/cos	11.8	Frustratingly Simple Few-Shot Object Detection
Meta-RCNN	11.2	Meta-RCNN: Meta Learning for Few-Shot Object Detection	-
BIOT(5-shot)	18.0	Balanced ID-OOD tradeoff transfer makes query based detectors good few shot learners	-
CD-ViTO	7.0	Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector
ViTDeT-FT	15.8	Exploring Plain Vision Transformer Backbones for Object Detection
DE-ViT-FT	5.4	Detect Everything with Few Examples
BIOT(10-shot)	20.4	Balanced ID-OOD tradeoff transfer makes query based detectors good few shot learners	-

0 of 10 row(s) selected.