Discriminative Semantic Transitive Consistency for Cross-Modal Learning
This addresses cross-modal retrieval for applications like image-text matching, but appears incremental with hybrid constraints.
The paper tackles the problem of learning a shared representation space for cross-modal retrieval by introducing Discriminative Semantic Transitive Consistency, which ensures data points remain correctly classified after modality transfer, alongside traditional distance minimization and semantic cycle-consistency. The result is empirically demonstrated better performance with clear ablation studies and qualitative support.
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.