Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations

TL;DR

This paper introduces Css-Net, a consensus learning framework for composed image retrieval that mitigates triplet ambiguity by leveraging diverse compositors and inter-compositor interaction, leading to improved retrieval accuracy.

Contribution

The paper proposes Css-Net, a novel consensus network with multiple compositors and a divergence loss to address triplet ambiguity in image-text retrieval tasks.

Findings

Achieves a 2.77% increase in R@10 on FashionIQ

Attains a 6.67% boost in R@50 on benchmark datasets

Demonstrates robustness against noisy triplet annotations

Abstract

Composed image retrieval extends content-based image retrieval systems by enabling users to search using reference images and captions that describe their intention. Despite great progress in developing image-text compositors to extract discriminative visual-linguistic features, we identify a hitherto overlooked issue, triplet ambiguity, which impedes robust feature extraction. Triplet ambiguity refers to a type of semantic ambiguity that arises between the reference image, the relative caption, and the target image. It is mainly due to the limited representation of the annotated text, resulting in many noisy triplets where multiple visually dissimilar candidate images can be matched to an identical reference pair (i.e., a reference image + a relative caption). To address this challenge, we propose the Consensus Network (Css-Net), inspired by the psychological concept that groups outperform individuals. Css-Net comprises two core components: (1) a consensus module with four diverse compositors, each generating distinct image-text embeddings, fostering complementary feature extraction and mitigating dependence on any single, potentially biased compositor; (2) a Kullback-Leibler divergence loss that encourages learning of inter-compositor interactions to promote consensual outputs. During evaluation, the decisions of the four compositors are combined through a weighting scheme, enhancing overall agreement. On benchmark datasets, particularly FashionIQ, Css-Net demonstrates marked improvements. Notably, it achieves significant recall gains, with a 2.77% increase in R@10 and 6.67% boost in R@50, underscoring its competitiveness in addressing the fundamental limitations of existing methods.