Litcius/Paper detail

Contrastive Label Correlation Enhanced Unified Hashing Encoder for Cross-modal Retrieval

Hongfa Wu, Lisai Zhang, Qingcai Chen, Yimeng Deng, Joanna Siebert, Yunpeng Han, Zhonghua Li, Dejiang Kong, Zhao Cao

2022Proceedings of the 31st ACM International Conference on Information & Knowledge Management18 citationsDOI

Abstract

Cross-modal hashing (CMH) has been widely used in multimedia retrieval applications for its low storage cost and fast indexing speed. Thanks to the success of deep learning, cross-modal hashing has made significant progress with high-quality deep features. However, the modal gap is still a crucial bottleneck for existing cross-modal hashing methods: the commonly used convolutional neural network and bag-of-words encoders are customized for single modal prior, limiting the models to learn semantics representation in a cross-modal space. To overcome modality heterogeneity, we propose a shared transformer encoder (UniHash) to unify the cross-modal hashing into the same semantic space. A contrastive label correlation learning (CLC) loss using the category labels as modality bridge is designed together to improve the representation quality. Moreover, we take advantage of the multi-hot label space and propose a negative label generation (NegLG) strategy to get richer and uniformly distributed negative labels for contrast. Extensive experiments on three benchmarks verify the advantage of our proposed method. Besides, the proposed UniHash outperforms state-of-the-art cross-modal hashing methods significantly, establishing a new important baseline for the cross-modal hashing research. Codes are released github.com/idealwhite/Unihash.

Topics & Concepts

Computer scienceHash functionModalAutoencoderFeature hashingArtificial intelligenceDynamic perfect hashingEncoderFeature learningModality (human–computer interaction)BottleneckUniversal hashingConvolutional neural networkDeep learningPattern recognition (psychology)Hash tableDouble hashingOperating systemEmbedded systemComputer securityChemistryPolymer chemistryAdvanced Image and Video Retrieval TechniquesMultimodal Machine Learning ApplicationsVideo Surveillance and Tracking Methods
Contrastive Label Correlation Enhanced Unified Hashing Encoder for Cross-modal Retrieval | Litcius