Towards Unbiased Cross-Modal Representation Learning for Food Image-to-Recipe Retrieval

TL;DR

This paper introduces a causal inference approach to reduce bias in cross-modal food image-to-recipe retrieval, significantly improving retrieval accuracy by accounting for confounders like ingredients.

Contribution

It models bias using causal theory and proposes a simple, effective debiasing module that achieves state-of-the-art results on the Recipe1M dataset.

Findings

Achieves MedR=1 on Recipe1M dataset across various data sizes.

Proposes a causal intervention-based reformulation for bias reduction.

Demonstrates improved retrieval performance with a plug-and-play debiasing module.

Abstract

This paper addresses the challenges of learning representations for recipes and food images in the cross-modal retrieval problem. As the relationship between a recipe and its cooked dish is cause-and-effect, treating a recipe as a text source describing the visual appearance of a dish for learning representation, as the existing approaches, will create bias misleading image-and-recipe similarity judgment. Specifically, a food image may not equally capture every detail in a recipe, due to factors such as the cooking process, dish presentation, and image-capturing conditions. The current representation learning tends to capture dominant visual-text alignment while overlooking subtle variations that determine retrieval relevance. In this paper, we model such bias in cross-modal representation learning using causal theory. The causal view of this problem suggests ingredients as one of the confounder sources and a simple backdoor adjustment can alleviate the bias. By causal intervention, we reformulate the conventional model for food-to-recipe retrieval with an additional term to remove the potential bias in similarity judgment. Based on this theory-informed formulation, we empirically prove the oracle performance of retrieval on the Recipe1M dataset to be MedR=1 across the testing data sizes of 1K, 10K, and even 50K. We also propose a plug-and-play neural module, which is essentially a multi-label ingredient classifier for debiasing. New state-of-the-art search performances are reported on the Recipe1M dataset.