Discriminative Semantic Transitive Consistency For Cross-modal Learning

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 abla

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyparida2021discriminative

Related papers

• Adversarial Cross-modal Retrieval Via Learning And Transferring Single-modal Similarities (2019)8.60
• Preserving Semantic Neighborhoods For Robust Cross-modal Retrieval (2020)10.07
• Discriminative Supervised Subspace Learning For Cross-modal Retrieval (2022)0.00
• Deep Reversible Consistency Learning For Cross-modal Retrieval (2025)7.81
• Swamp: Swapped Assignment Of Multi-modal Pairs For Cross-modal Retrieval (2021)0.00
• Tsvc:tripartite Learning With Semantic Variation Consistency For Robust Image-text Retrieval (2025)3.58
• Maximal Matching Matters: Preventing Representation Collapse For Robust Cross-modal Retrieval (2025)2.26
• Multimodal Representation Alignment For Cross-modal Information Retrieval (2025)0.00