Causal Transportability for Visual Recognition

04/26/2022
by   Chengzhi Mao, et al.
5

Visual representations underlie object recognition tasks, but they often contain both robust and non-robust features. Our main observation is that image classifiers may perform poorly on out-of-distribution samples because spurious correlations between non-robust features and labels can be changed in a new environment. By analyzing procedures for out-of-distribution generalization with a causal graph, we show that standard classifiers fail because the association between images and labels is not transportable across settings. However, we then show that the causal effect, which severs all sources of confounding, remains invariant across domains. This motivates us to develop an algorithm to estimate the causal effect for image classification, which is transportable (i.e., invariant) across source and target environments. Without observing additional variables, we show that we can derive an estimand for the causal effect under empirical assumptions using representations in deep models as proxies. Theoretical analysis, empirical results, and visualizations show that our approach captures causal invariances and improves overall generalization.

READ FULL TEXT
research
05/26/2023

Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers

To address the problem of NLP classifiers learning spurious correlations...
research
12/22/2020

Generative Interventions for Causal Learning

We introduce a framework for learning robust visual representations that...
research
08/19/2021

Causal Attention for Unbiased Visual Recognition

Attention module does not always help deep models learn causal features ...
research
06/02/2021

Towards Robust Classification Model by Counterfactual and Invariant Data Generation

Despite the success of machine learning applications in science, industr...
research
10/06/2022

Domain Generalization via Contrastive Causal Learning

Domain Generalization (DG) aims to learn a model that can generalize wel...
research
02/24/2021

Nonlinear Invariant Risk Minimization: A Causal Approach

Due to spurious correlations, machine learning systems often fail to gen...
research
08/22/2017

On Image Classification: Correlation v.s. Causality

Image classification is one of the fundamental problems in computer visi...

Please sign up or login with your details

Forgot password? Click here to reset