Probabilistic Embeddings for Cross-Modal Retrieval
arXiv:2101.05068
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 that it not only improves the retrieval performance over its deterministic counterpart but also provides uncertainty estimates that render the embeddings more interpretable. Code is available at https://github.com/naver-ai/pcme
arXiv commentAccepted to CVPR 2021; Code is available at https://github.com/naver-ai/pcme
References in corpus (11)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Auto-Encoding Variational Bayes
- Improved Regularization of Convolutional Neural Networks with Cutout
- Microsoft COCO Captions: Data Collection and Evaluation Server
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
- Word Representations via Gaussian Embedding
- NSML: Meet the MLaaS platform with a real-world case study
- Fisher Vectors Derived from Hybrid Gaussian-Laplacian Mixture Models for Image Annotation
- Modeling Uncertainty with Hedged Instance Embedding
- Stochastic Prototype Embeddings