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.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/MediaBrain-SJTU/GSC

공식 코드

Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning

https://github.com/alipay/PC2-NoiseofWeb

공식 코드

PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval

https://github.com/hhc1997/l2rm

공식 코드

Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval

https://github.com/hhc1997/mscn

공식 코드

Noisy Correspondence Learning with Meta Similarity Correction

https://github.com/qinyang79/crcl

공식 코드

Cross-modal Active Complementary Learning with Self-refining Correspondence

https://github.com/qxzha/ReCon

공식 코드

ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning

https://github.com/xu5zhao/bicro

공식 코드

BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency

https://github.com/zhangxu0963/npc

공식 코드

Negative Pre-aware for Noisy Cross-modal Matching

https://github.com/AAA-Zheng/LG_ITM

https://github.com/XLearning-SCU/2021-NeurIPS-NCR

https://github.com/XLearning-SCU/2024-TIP-CREAM

https://github.com/leolee99/osa

Negative Pre-aware for Noisy Cross-modal Matching

https://github.com/penghu-cs/RCL

https://github.com/qinyang79/decl

https://github.com/qxzha/UGNCL

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.