Skip to yearly menu bar Skip to main content

In-Person Oral presentation / top 25% paper

Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations

Polina Kirichenko · Pavel Izmailov · Andrew Wilson



Neural network classifiers can largely rely on simple spurious features, such as image backgrounds, to make predictions. However, even in these cases, we show that they still often learn core features associated with the desired attributes of the data, contrary to recent findings. Inspired by this insight, we demonstrate that simple last layer retraining can match or outperform state-of-the-art approaches on spurious correlation benchmarks, but with profoundly lower complexity and computational expenses. Moreover, we show that last layer retraining on large ImageNet-trained models can also significantly reduce reliance on background and texture information, improving robustness to covariate shift, after only minutes of training on a single GPU.

Chat is not available.