Cross-Modal Retrieval and Synthesis (X-MRS): Closing the Modality Gap in Shared Representation Learning

2 Dec 2020  ·  Ricardo Guerrero, Hai Xuan Pham, Vladimir Pavlovic ·

Computational food analysis (CFA) naturally requires multi-modal evidence of a particular food, e.g., images, recipe text, etc. A key to making CFA possible is multi-modal shared representation learning, which aims to create a joint representation of the multiple views (text and image) of the data. In this work we propose a method for food domain cross-modal shared representation learning that preserves the vast semantic richness present in the food data. Our proposed method employs an effective transformer-based multilingual recipe encoder coupled with a traditional image embedding architecture. Here, we propose the use of imperfect multilingual translations to effectively regularize the model while at the same time adding functionality across multiple languages and alphabets. Experimental analysis on the public Recipe1M dataset shows that the representation learned via the proposed method significantly outperforms the current state-of-the-arts (SOTA) on retrieval tasks. Furthermore, the representational power of the learned representation is demonstrated through a generative food image synthesis model conditioned on recipe embeddings. Synthesized images can effectively reproduce the visual appearance of paired samples, indicating that the learned representation captures the joint semantics of both the textual recipe and its visual content, thus narrowing the modality gap.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Cross-Modal Retrieval Recipe1M X-MRS Image-to-text R@1 64 # 5
Text-to-image R@1 63.9 # 5


No methods listed for this paper. Add relevant methods here