paper-with-me

홈 › Papers

Vision Language Pre-training by Contrastive Learning with Cross-Modal Similarity Regulation

2023-05-08 · Chaoya Jiang, Wei Ye, Haiyang Xu, Miang yan, Shikun Zhang, Jie Zhang, Fei Huang

Cross-modal contrastive learning in vision language pretraining (VLP) faces the challenge of (partial) false negatives. In this paper, we study this problem from the perspective of Mutual Information (MI) optimization. It is common sense that InfoNCE loss used in contrastive learning will maximize the lower bound of MI between anchors and their positives, while we theoretically prove that MI involving negatives also matters when noises commonly exist. Guided by a more general lower bound form for optimization, we propose a contrastive learning strategy regulated by progressively refined cross-modal similarity, to more accurately optimize MI between an image/text anchor and its negative texts/images instead of improperly minimizing it. Our method performs competitively on four downstream cross-modal tasks and systematically balances the beneficial and harmful effects of (partial) false negative samples under theoretical guidance.

📄 PDF Abstract BibTeX arXiv:2305.04474

Code (0)

등록된 구현이 없습니다.

Tasks

Common Sense ReasoningContrastive Learning

Methods 이 논문이 사용한 방법론

InfoNCE 설명 없음
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

CoCo-BERT: Improving Video-Language Pre-training with Contrastive Cross-modal Matching and Denoising

2021-12-14 · Jianjie Luo, Yehao Li, Yingwei Pan, Ting Yao 외

BERT-type structure has led to the revolution of vision-language pre-training and the achievement of state-of-the-art results on numerous vision-language downstream tasks. Existing solutions dominantly capitalize on the …

Cross-Modal RetrievalDecoderDenoisingLanguage Modeling+6

LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives

2026-07-01 · Lukas Kuhn, Giuseppe Serra, Randall Balestriero, Florian Buettner arxiv

Vision-language pretraining remains dominated by contrastive objectives, whereas vision-only self-supervised learning has largely adopted non-contrastive methods. At the same time, the role of vision-language encoders ha…

Self-Supervised LearningSemantic Segmentation

On the Language Encoder of Contrastive Cross-modal Models

2023-10-20 · Mengjie Zhao, Junya Ono, Zhi Zhong, Chieh-Hsin Lai 외

Contrastive cross-modal models such as CLIP and CLAP aid various vision-language (VL) and audio-language (AL) tasks. However, there has been limited investigation of and improvement in their language encoder, which is th…

cross-modal alignmentSentenceSentence EmbeddingSentence-Embedding

Vision-Language Pre-Training with Triple Contrastive Learning

2022-02-21 · CVPR 2022 1 · Jinyu Yang, Jiali Duan, Son Tran, Yi Xu 외

Vision-language representation learning largely benefits from image-text alignment through contrastive losses (e.g., InfoNCE loss). The success of this alignment strategy is attributed to its capability in maximizing the…

Contrastive Learningcross-modal alignmentCross-Modal RetrievalImage-text Retrieval+7

COOKIE: Contrastive Cross-Modal Knowledge Sharing Pre-Training for Vision-Language Representation

2021-01-01 · ICCV 2021 10 · Keyu Wen, Jin Xia, Yuanyuan Huang, Linyang Li 외

There has been a recent surge of interest in cross-modal pre-training. However, existed approaches pre-train a one-stream model to learn joint vision-language representation, which suffers from calculation explosion …

Contrastive LearningCross-Modal RetrievalImage RetrievalRetrieval+1