Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation

arXiv:2405.03649v1 Announce Type: new
Abstract: Deep neural classifiers tend to rely on spurious correlations between spurious attributes of inputs and targets to make predictions, which could jeopardize their generalization capability. Training classifiers robust to spurious correlations typically relies on annotations of spurious correlations in data, which are often expensive to get. In this paper, we tackle an annotation-free setting and propose a self-guided spurious correlation mitigation framework. Our framework automatically constructs fine-grained training labels tailored for a classifier obtained with …

abstract annotations arxiv capability classifiers correlation correlations cs.cv cs.lg data inputs predictions robust targets training type