Discriminative Semantic Transitive Consistency for Cross-Modal Learning

TL;DR

This paper introduces a novel cross-modal learning approach that enforces semantic transitive consistency and cycle-consistency to improve retrieval accuracy across different data modalities.

Contribution

It proposes the Discriminative Semantic Transitive Consistency property and combines it with traditional distance minimization and cycle-consistency for enhanced cross-modal representation learning.

Findings

Improved retrieval performance demonstrated through experiments.

Clear ablation studies showing the contribution of each component.

Qualitative results supporting the effectiveness of the proposed method.

Abstract

Cross-modal retrieval is generally performed by projecting and aligning the data from two different modalities onto a shared representation space. This shared space often also acts as a bridge for translating the modalities. We address the problem of learning such representation space by proposing and exploiting the property of Discriminative Semantic Transitive Consistency -- ensuring that the data points are correctly classified even after being transferred to the other modality. Along with semantic transitive consistency, we also enforce the traditional distance minimizing constraint which makes the projections of the corresponding data points from both the modalities to come closer in the representation space. We analyze and compare the contribution of both the loss terms and their interaction, for the task. In addition, we incorporate semantic cycle-consistency for each of the modality. We empirically demonstrate better performance owing to the different components with clear ablation studies. We also provide qualitative results to support the proposals.