Domain Adaptive Hashing Retrieval via VLM Assisted Pseudo-Labeling and Dual Space Adaptation

Jingyao Li, Zhanshan Li, Shuai Lü

Keywords: Domain Adaptive Hashing, Image Retrieval, Pseudo-Labeling Strategy, Unsupervised Domain Adaptation

TL;DR: We propose a VLM-assisted dual-space adaptation framework to improve unsupervised domain adaptive hashing by calibrating pseudo-labels and decoupling feature and Hamming space alignment.

Abstract: Unsupervised domain adaptive hashing has emerged as a promising approach for efficient and memory-friendly cross-domain retrieval. It leverages the model learned on labeled source domains to generate compact binary codes for unlabeled target domain samples, ensuring that semantically similar samples are mapped to nearby points in the Hamming space. Existing methods typically apply domain adaptation techniques to the feature space or the Hamming space, especially pseudo-labeling and feature alignment. However, the inherent noise of pseudo-labels and the insufficient exploration of complementary knowledge across spaces hinder the ability of the adapted model. To address these challenges, we propose a Vision-language model assisted Pseudo-labeling and Dual Space adaptation (VPDS) method. Motivated by the strong zero-shot generalization capabilities of pre-trained vision-language models (VLMs), VPDS leverages VLMs to calibrate pseudo-labels, thereby mitigating pseudo-label bias. Furthermore, to simultaneously utilize the semantic richness of high-dimensional feature space and preserve discriminative efficiency of low-dimensional Hamming space, we introduce a dual space adaptation approach that performs independent alignment within each space. Extensive experiments on three benchmark datasets demonstrate that VPDS consistently outperforms existing methods in both cross-domain and single-domain retrieval tasks, highlighting its effectiveness and superiority.

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 8000