HHF: Hashing-guided Hinge Function for Deep Hashing Retrieval
Chengyin Xu, Zenghao Chai, Zhengzhuo Xu, Hongjia Li, Qiruyi Zuo,, Lingyu Yang, Chun Yuan

TL;DR
This paper introduces HHF, a novel hashing-guided hinge function that balances metric learning and quantization in deep hashing, significantly improving image retrieval accuracy across multiple datasets.
Contribution
The paper proposes a new HHF method that explicitly balances metric and quantization terms, overcoming conflicts in deep hashing and enhancing retrieval performance.
Findings
HHF outperforms existing deep hashing methods on CIFAR-10, CIFAR-100, ImageNet, and MS-COCO.
The method is robust and adaptable to other deep hashing techniques.
Extensive experiments validate the effectiveness of HHF in large-scale image retrieval.
Abstract
Deep hashing has shown promising performance in large-scale image retrieval. However, latent codes extracted by Deep Neural Networks (DNNs) will inevitably lose semantic information during the binarization process, which damages the retrieval accuracy and makes it challenging. Although many existing approaches perform regularization to alleviate quantization errors, we figure out an incompatible conflict between metric learning and quantization learning. The metric loss penalizes the inter-class distances to push different classes unconstrained far away. Worse still, it tends to map the latent code deviate from ideal binarization point and generate severe ambiguity in the binarization process. Based on the minimum distance of the binary linear code, we creatively propose Hashing-guided Hinge Function (HHF) to avoid such conflict. In detail, the carefully-designed inflection point, which…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image and Video Retrieval Techniques · Advanced Neural Network Applications · Image Retrieval and Classification Techniques
