Improved Deep Classwise Hashing With Centers Similarity Learning for Image Retrieval

TL;DR

This paper introduces an improved deep classwise hashing method that simultaneously learns hashing codes and class centers, utilizing a two-step centers similarity learning strategy to enhance image retrieval performance.

Contribution

It proposes a novel two-step centers similarity learning approach that improves classwise hashing by making class centers more discriminative and compact.

Findings

Outperforms baseline methods on benchmark datasets.

Produces more compact and discriminative hashing codes.

Achieves superior retrieval accuracy across various metrics.

Abstract

Deep supervised hashing for image retrieval has attracted researchers' attention due to its high efficiency and superior retrieval performance. Most existing deep supervised hashing works, which are based on pairwise/triplet labels, suffer from the expensive computational cost and insufficient utilization of the semantics information. Recently, deep classwise hashing introduced a classwise loss supervised by class labels information alternatively; however, we find it still has its drawback. In this paper, we propose an improved deep classwise hashing, which enables hashing learning and class centers learning simultaneously. Specifically, we design a two-step strategy on center similarity learning. It interacts with the classwise loss to attract the class center to concentrate on the intra-class samples while pushing other class centers as far as possible. The centers similarity learning contributes to generating more compact and discriminative hashing codes. We conduct experiments on three benchmark datasets. It shows that the proposed method effectively surpasses the original method and outperforms state-of-the-art baselines under various commonly-used evaluation metrics for image retrieval.