DeepAI AI Chat
Log In Sign Up

HHF: Hashing-guided Hinge Function for Deep Hashing Retrieval

by   Chengyin Xu, et al.
Tsinghua University

Deep hashing has shown promising performance in large-scale image retrieval. However, latent codes extracted by Deep Neural Network (DNN) will inevitably lose semantic information during the binarization process, which damages the retrieval efficiency and make it challenging. Although many existing approaches perform regularization to alleviate quantization errors, we figure out an incompatible conflict between the metric and quantization losses. 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, Hashing-guided Hinge Function (HHF) is proposed to avoid such conflict. In detail, we carefully design a specific inflection point, which relies on the hash bit length and category numbers to balance metric learning and quantization learning. Such a modification prevents the network from falling into local metric optimal minima in deep hashing. Extensive experiments in CIFAR-10, CIFAR-100, ImageNet, and MS-COCO show that HHF consistently outperforms existing techniques, and is robust and flexible to transplant into other methods.


page 1

page 8

page 9

page 10


Unsupervised Triplet Hashing for Fast Image Retrieval

Hashing has played a pivotal role in large-scale image retrieval. With t...

Deep Asymmetric Hashing with Dual Semantic Regression and Class Structure Quantization

Recently, deep hashing methods have been widely used in image retrieval ...

Vision Transformer Hashing for Image Retrieval

Deep learning has shown a tremendous growth in hashing techniques for im...

Self-Distilled Hashing for Deep Image Retrieval

In hash-based image retrieval systems, the transformed input from the or...

Hard Example Guided Hashing for Image Retrieval

Compared with the traditional hashing methods, deep hashing methods gene...

Push for Quantization: Deep Fisher Hashing

Current massive datasets demand light-weight access for analysis. Discre...

Deep Momentum Uncertainty Hashing

Discrete optimization is one of the most intractable problems in deep ha...