TSVC:Tripartite Learning with Semantic Variation Consistency for Robust Image-Text Retrieval

TL;DR

This paper introduces TSVC, a tripartite learning framework with semantic variation consistency, designed to improve robustness in image-text retrieval under noisy correspondence conditions, outperforming existing methods especially with high noise.

Contribution

The paper proposes a novel tripartite cooperative learning mechanism and a soft label estimation method to enhance robustness against annotation noise in cross-modal retrieval.

Findings

TSVC outperforms existing methods under high noise ratios.

The tripartite model maintains stable training and high accuracy.

The soft label estimation effectively quantifies noise and improves label quality.

Abstract

Cross-modal retrieval maps data under different modality via semantic relevance. Existing approaches implicitly assume that data pairs are well-aligned and ignore the widely existing annotation noise, i.e., noisy correspondence (NC). Consequently, it inevitably causes performance degradation. Despite attempts that employ the co-teaching paradigm with identical architectures to provide distinct data perspectives, the differences between these architectures are primarily stemmed from random initialization. Thus, the model becomes increasingly homogeneous along with the training process. Consequently, the additional information brought by this paradigm is severely limited. In order to resolve this problem, we introduce a Tripartite learning with Semantic Variation Consistency (TSVC) for robust image-text retrieval. We design a tripartite cooperative learning mechanism comprising a Coordinator, a Master, and an Assistant model. The Coordinator distributes data, and the Assistant model supports the Master model's noisy label prediction with diverse data. Moreover, we introduce a soft label estimation method based on mutual information variation, which quantifies the noise in new samples and assigns corresponding soft labels. We also present a new loss function to enhance robustness and optimize training effectiveness. Extensive experiments on three widely used datasets demonstrate that, even at increasing noise ratios, TSVC exhibits significant advantages in retrieval accuracy and maintains stable training performance.