Saved in:
Bibliographic Details
Main Authors: Wang, Haoran, He, Dongliang, Wu, Wenhao, Xia, Boyang, Yang, Min, Li, Fu, Yu, Yunlong, Ji, Zhong, Ding, Errui, Wang, Jingdong
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2208.09843
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917362552274944
author Wang, Haoran
He, Dongliang
Wu, Wenhao
Xia, Boyang
Yang, Min
Li, Fu
Yu, Yunlong
Ji, Zhong
Ding, Errui
Wang, Jingdong
author_facet Wang, Haoran
He, Dongliang
Wu, Wenhao
Xia, Boyang
Yang, Min
Li, Fu
Yu, Yunlong
Ji, Zhong
Ding, Errui
Wang, Jingdong
contents Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative image-text pairs, the capability of constrastive learning is restricted by manually weighting negative pairs as well as unawareness of external knowledge. In this paper, we propose our novel Coupled Diversity-Sensitive Momentum Constrastive Learning (CODER) for improving cross-modal representation. Firstly, a novel diversity-sensitive contrastive learning (DCL) architecture is invented. We introduce dynamic dictionaries for both modalities to enlarge the scale of image-text pairs, and diversity-sensitiveness is achieved by adaptive negative pair weighting. Furthermore, two branches are designed in CODER. One learns instance-level embeddings from image/text, and it also generates pseudo online clustering labels for its input image/text based on their embeddings. Meanwhile, the other branch learns to query from commonsense knowledge graph to form concept-level descriptors for both modalities. Afterwards, both branches leverage DCL to align the cross-modal embedding spaces while an extra pseudo clustering label prediction loss is utilized to promote concept-level representation learning for the second branch. Extensive experiments conducted on two popular benchmarks, i.e. MSCOCO and Flicker30K, validate CODER remarkably outperforms the state-of-the-art approaches. Our code is available at: https://github.com/BruceW91/CODER.
format Preprint
id arxiv_https___arxiv_org_abs_2208_09843
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval
Wang, Haoran
He, Dongliang
Wu, Wenhao
Xia, Boyang
Yang, Min
Li, Fu
Yu, Yunlong
Ji, Zhong
Ding, Errui
Wang, Jingdong
Computer Vision and Pattern Recognition
Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative image-text pairs, the capability of constrastive learning is restricted by manually weighting negative pairs as well as unawareness of external knowledge. In this paper, we propose our novel Coupled Diversity-Sensitive Momentum Constrastive Learning (CODER) for improving cross-modal representation. Firstly, a novel diversity-sensitive contrastive learning (DCL) architecture is invented. We introduce dynamic dictionaries for both modalities to enlarge the scale of image-text pairs, and diversity-sensitiveness is achieved by adaptive negative pair weighting. Furthermore, two branches are designed in CODER. One learns instance-level embeddings from image/text, and it also generates pseudo online clustering labels for its input image/text based on their embeddings. Meanwhile, the other branch learns to query from commonsense knowledge graph to form concept-level descriptors for both modalities. Afterwards, both branches leverage DCL to align the cross-modal embedding spaces while an extra pseudo clustering label prediction loss is utilized to promote concept-level representation learning for the second branch. Extensive experiments conducted on two popular benchmarks, i.e. MSCOCO and Flicker30K, validate CODER remarkably outperforms the state-of-the-art approaches. Our code is available at: https://github.com/BruceW91/CODER.
title CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2208.09843