Papers with Code 아카이브
Cross-modal retrieval with noisy correspondence
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 48
Noisy correspondence learning aims to eliminate the negative impact of the mismatched pairs (e.g., false positives/negatives) instead of annotation errors in several tasks.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval
UGNCL: Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal Matching
Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning
Cross-modal Retrieval with Noisy Correspondence via Consistency Refining and Mining
NAC: Mitigating Noisy Correspondence in Cross-Modal Matching Via Neighbor Auxiliary Corrector
REPAIR: Rank Correlation and Noisy Pair Half-replacing with Memory for Noisy Correspondence
Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval
Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation
Negative Pre-aware for Noisy Cross-modal Matching
Cross-modal Active Complementary Learning with Self-refining Correspondence
Learning From Noisy Correspondence With Tri-Partition for Cross-Modal Matching
Noisy Correspondence Learning with Meta Similarity Correction
Integrating Language Guidance Into Image-Text Matching for Correcting False Negatives
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
Cross-Modal Retrieval with Partially Mismatched Pairs
DetFusion: A Detection-driven Infrared and Visible Image Fusion Network
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.