HyperAI초신경

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

한국어

HyperAI초신경

Weakly Supervised Object Detection On Comic2K

평가 지표

MAP

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	MAP	Paper Title	Repository
H2FA R-CNN (+extra)	53.0	H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection	-
DASS-Detector (YOLOX Tiny)	67.41	Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings
DT+PL (+extra)	42.2	Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation
MI-max	27	Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts
ICCM	37.1	Informative and Consistent Correspondence Mining for Cross-Domain Weakly Supervised Object Detection	-
H2FA R-CNN	46.4	H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection	-
DT+PL	37.2	Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation
TADP	57.4	Text-image Alignment for Diffusion-based Perception

0 of 8 row(s) selected.