Probabilistic Embeddings For Cross-modal Retrieval

Abstract

Cross-modal retrieval methods build a common representation space for samples from multiple modalities, typically from the vision and the language domains. For images and their captions, the multiplicity of the correspondences makes the task particularly challenging. Given an image (respectively a caption), there are multiple captions (respectively images) that equally make sense. In this paper, we argue that deterministic functions are not sufficiently powerful to capture such one-to-many correspondences. Instead, we propose to use Probabilistic Cross-Modal Embedding (PCME), where samples from the different modalities are represented as probabilistic distributions in the common embedding space. Since common benchmarks such as COCO suffer from non-exhaustive annotations for cross-modal matches, we propose to additionally evaluate retrieval on the CUB dataset, a smaller yet clean database where all possible image-caption pairs are annotated. We extensively ablate PCME and demonstrate th

Stats

• citations208
• S2 citations—
• github stars140
• HF likes0
• heat score21.70
• arxiv keychun2021probabilistic

Related papers

• Uncertainty-based Cross-modal Retrieval With Probabilistic Representations (2022)0.00
• Probabilistic Compositional Embeddings For Multimodal Image Retrieval (2022)13.80
• Improving Cross-modal Retrieval With Set Of Diverse Embeddings (2022)13.55
• PC\(^2\): Pseudo-classification Based Pseudo-captioning For Noisy Correspondence Learning In Cross-modal Retrieval (2024)9.23
• Revisiting Cross Modal Retrieval (2018)0.00
• Maximal Matching Matters: Preventing Representation Collapse For Robust Cross-modal Retrieval (2025)2.26
• COBRA: Contrastive Bi-modal Representation Algorithm (2020)0.00
• Aligning Multilingual Word Embeddings For Cross-modal Retrieval Task (2019)2.26