Confounder Identification-free Causal Visual Feature Learning

TL;DR

This paper introduces CICF, a novel method for learning causal visual features without needing to identify confounders, improving model generalization across diverse domains.

Contribution

CICF employs a front-door intervention approach and connects causal learning with meta-learning, offering a new way to learn confounder-free features without explicit confounder identification.

Findings

Achieves state-of-the-art results on domain generalization benchmarks.

Effectively learns causal features that enhance model robustness.

Uncovers the theoretical link between CICF and MAML.

Abstract

Confounders in deep learning are in general detrimental to model's generalization where they infiltrate feature representations. Therefore, learning causal features that are free of interference from confounders is important. Most previous causal learning based approaches employ back-door criterion to mitigate the adverse effect of certain specific confounder, which require the explicit identification of confounder. However, in real scenarios, confounders are typically diverse and difficult to be identified. In this paper, we propose a novel Confounder Identification-free Causal Visual Feature Learning (CICF) method, which obviates the need for identifying confounders. CICF models the interventions among different samples based on front-door criterion, and then approximates the global-scope intervening effect upon the instance-level interventions from the perspective of optimization. In this way, we aim to find a reliable optimization direction, which avoids the intervening effects of confounders, to learn causal features. Furthermore, we uncover the relation between CICF and the popular meta-learning strategy MAML, and provide an interpretation of why MAML works from the theoretical perspective of causal learning for the first time. Thanks to the effective learning of causal features, our CICF enables models to have superior generalization capability. Extensive experiments on domain generalization benchmark datasets demonstrate the effectiveness of our CICF, which achieves the state-of-the-art performance.