HyperAI초신경

홈 뉴스 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Cross Domain Few Shot Object Detection On 2

평가 지표

mAP

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	mAP	Paper Title	Repository
FSCE	21.9	FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
Detic-FT	15.4	Detecting Twenty-thousand Classes using Image-level Supervision
ViTDeT-FT	29.4	Exploring Plain Vision Transformer Backbones for Object Detection
BIOT	31.1	Balanced ID-OOD tradeoff transfer makes query based detectors good few shot learners	-
TFA w/cos	20.5	Frustratingly Simple Few-Shot Object Detection
CD-ViTO	30.8	Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector
DeFRCN	22.9	DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
DE-ViT-FT	25.6	Detect Everything with Few Examples
Meta-RCNN	20.6	Meta-RCNN: Meta Learning for Few-Shot Object Detection	-

0 of 9 row(s) selected.