HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval

2026-04-20

AI Summary

This work addresses the noisy triplet correspondence (NTC) problem in compositional image retrieval, which arises from the high annotation cost and subjectivity of triplet labeling. To tackle this challenge, the authors propose a robust progressive learning framework that introduces, for the first time, a sample cleanliness assessment mechanism based on mutual information transfer rate. The framework employs a dual-model collaborative strategy with dual consistency constraints between historical and current models, effectively simulating the human habit formation process to mitigate semantic bias and noise interference. Extensive experiments on two standard benchmarks demonstrate that the proposed method consistently outperforms existing approaches across various noise ratios, achieving superior robustness and retrieval performance.

Technology Category

• Computer Vision: Image and Video Retrieval
• Machine Learning: Multi-instance/Multi-view Learning
• Natural Language Processing: Safety and Robustness

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Composed Image Retrieval (CIR) is a flexible image retrieval paradigm that enables users to accurately locate the target image through a multimodal query composed of a reference image and modification text. Although this task has demonstrated promising applications in personalized search and recommendation systems, it encounters a severe challenge in practical scenarios known as the Noise Triplet Correspondence (NTC) problem. This issue primarily arises from the high cost and subjectivity involved in annotating triplet data. To address this problem, we identify two central challenges: the precise estimation of composed semantic discrepancy and the insufficient progressive adaptation to modification discrepancy. To tackle these challenges, we propose a cHrono-synergiA roBust progressIve learning framework for composed image reTrieval (HABIT), which consists of two core modules. First, the Mutual Knowledge Estimation Module quantifies sample cleanliness by calculating the Transition Rate of mutual information between the composed feature and the target image, thereby effectively identifying clean samples that align with the intended modification semantics. Second, the Dual-consistency Progressive Learning Module introduces a collaborative mechanism between the historical and current models, simulating human habit formation to retain good habits and calibrate bad habits, ultimately enabling robust learning under the presence of NTC. Extensive experiments conducted on two standard CIR datasets demonstrate that HABIT significantly outperforms most methods under various noise ratios, exhibiting superior robustness and retrieval performance. Codes are available at https://github.com/Lee-zixu/HABIT

Problem

• Composed Image Retrieval
• Noise Triplet Correspondence
• Multimodal Query
• Semantic Discrepancy
• Robust Learning

Innovation

• Composed Image Retrieval
• Noise Triplet Correspondence
• Mutual Knowledge Estimation
• Progressive Learning
• Robust Learning