Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Mitigating Cross-modal Representation Bias for Multicultural Image-to-Recipe Retrieval

About

Existing approaches for image-to-recipe retrieval have the implicit assumption that a food image can fully capture the details textually documented in its recipe. However, a food image only reflects the visual outcome of a cooked dish and not the underlying cooking process. Consequently, learning cross-modal representations to bridge the modality gap between images and recipes tends to ignore subtle, recipe-specific details that are not visually apparent but are crucial for recipe retrieval. Specifically, the representations are biased to capture the dominant visual elements, resulting in difficulty in ranking similar recipes with subtle differences in use of ingredients and cooking methods. The bias in representation learning is expected to be more severe when the training data is mixed of images and recipes sourced from different cuisines. This paper proposes a novel causal approach that predicts the culinary elements potentially overlooked in images, while explicitly injecting these elements into cross-modal representation learning to mitigate biases. Experiments are conducted on the standard monolingual Recipe1M dataset and a newly curated multilingual multicultural cuisine dataset. The results indicate that the proposed causal representation learning is capable of uncovering subtle ingredients and cooking actions and achieves impressive retrieval performance on both monolingual and multilingual multicultural datasets.

Qing Wang, Chong-Wah Ngo, Yu Cao, Ee-Peng Lim• 2025

Related benchmarks

TaskDatasetResultRank
Image-to-recipe retrievalRecipe1M 10k setup (test)
Recall@151.7
125
Recipe-to-image retrievalRecipe1M 10k setup (test)
R@152.2
120
Image-to-recipe retrievalRecipe1M 1k setup (test)
Recall@179.1
116
Recipe-to-image retrievalRecipe1M 1k setup (test)
Recall@178.3
110
Showing 4 of 4 rows

Other info

Follow for update