Towards Robust Classification Model by Counterfactual and Invariant Data Generation

Despite the success of machine learning applications in science, industry, and society in general, many approaches are known to be non-robust, often relying on spurious correlations to make predictions. Spuriousness occurs when some features correlate with labels but are not causal; relying on such features prevents models from generalizing to unseen environments where such correlations break. In this work, we focus on image classification and propose two data generation processes to reduce spuriousness. Given human annotations of the subset of the features responsible (causal) for the labels (e.g. bounding boxes), we modify this causal set to generate a surrogate image that no longer has the same label (i.e. a counterfactual image). We also alter non-causal features to generate images still recognized as the original labels, which helps to learn a model invariant to these features. In several challenging datasets, our data generations outperform state-of-the-art methods in accuracy when spurious correlations break, and increase the saliency focus on causal features providing better explanations.

PDF Abstract CVPR 2021 PDF CVPR 2021 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Out-of-Distribution Generalization UrbanCars CF+F Aug BG Gap -16.0 # 1
CoObj Gap +0.4 # 1
BG+CoObj Gap -19.4 # 1

Methods


No methods listed for this paper. Add relevant methods here