Confounder Identification-free Causal Visual Feature Learning

11/26/2021
by   Xin Li, et al.
0

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.

READ FULL TEXT

page 8

page 12

research
05/10/2023

Clothes-Invariant Feature Learning by Causal Intervention for Clothes-Changing Person Re-identification

Clothes-invariant feature extraction is critical to the clothes-changing...
research
12/22/2020

Generative Interventions for Causal Learning

We introduce a framework for learning robust visual representations that...
research
05/18/2020

Causal Feature Learning for Utility-Maximizing Agents

Discovering high-level causal relations from low-level data is an import...
research
08/22/2022

Meta-Causal Feature Learning for Out-of-Distribution Generalization

Causal inference has become a powerful tool to handle the out-of-distrib...
research
03/13/2023

Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective

In recent years, we have witnessed the great advancement of Deep neural ...
research
10/11/2022

Finding and Listing Front-door Adjustment Sets

Identifying the effects of new interventions from data is a significant ...

Please sign up or login with your details

Forgot password? Click here to reset