Litcius/Paper detail

Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval

Haokun Wen, Xuemeng Song, Jianhua Yin, Jianlong Wu, Weili Guan, Liqiang Nie

2023IEEE Transactions on Pattern Analysis and Machine Intelligence24 citationsDOI

Abstract

The composed image retrieval (CIR) task aims to retrieve the desired target image for a given multimodal query, i.e., a reference image with its corresponding modification text. The key limitations encountered by existing efforts are two aspects: 1) ignoring the multiple query-target matching factors; 2) ignoring the potential unlabeled reference-target image pairs in existing benchmark datasets. To address these two limitations is non-trivial due to the following challenges: 1) how to effectively model the multiple matching factors in a latent way without direct supervision signals; 2) how to fully utilize the potential unlabeled reference-target image pairs to improve the generalization ability of the CIR model. To address these challenges, in this work, we first propose a CLIP-Transformer based muLtI-factor Matching Network (LIMN), which consists of three key modules: disentanglement-based latent factor tokens mining, dual aggregation-based matching token learning, and dual query-target matching modeling. Thereafter, we design an iterative dual self-training paradigm to further enhance the performance of LIMN by fully utilizing the potential unlabeled reference-target image pairs in a weakly-supervised manner. Specifically, we denote the iterative dual self-training paradigm enhanced LIMN as LIMN+. Extensive experiments on four datasets, including FashionIQ, Shoes, CIRR, and Fashion200 K, show that our proposed LIMN and LIMN+ significantly surpass the state-of-the-art baselines.

Topics & Concepts

Computer scienceMatching (statistics)Artificial intelligenceBenchmark (surveying)Image retrievalKey (lock)Pattern recognition (psychology)Factor (programming language)Dual (grammatical number)Image (mathematics)Machine learningGeneralizationTransformerData miningMathematicsLiteratureComputer securityGeodesyQuantum mechanicsStatisticsPhysicsArtGeographyMathematical analysisProgramming languageVoltageAdvanced Image and Video Retrieval TechniquesImage Retrieval and Classification TechniquesMultimodal Machine Learning Applications