Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
Neural network classifiers can largely rely on simple spurious features, such as 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.
Code (4)
Tasks
GPUOut-of-Distribution GeneralizationSimilar Papers 제목 키워드 기반
Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?
Models trained with empirical risk minimization (ERM) are known to learn to rely on spurious features, i.e., their prediction is based on undesired auxiliary features which are strongly correlated with class labels but l…
Annotation-Free Group Robustness via Loss-Based Resampling
It is well-known that training neural networks for image classification with empirical risk minimization (ERM) makes them vulnerable to relying on spurious attributes instead of causal ones for prediction. Previously, de…
Attributeimage-classificationImage ClassificationTowards Last-layer Retraining for Group Robustness with Fewer Annotations
Empirical risk minimization (ERM) of neural networks is prone to over-reliance on spurious correlations and poor generalization on minority groups. The recent deep feature reweighting (DFR) technique achieves state-of-th…
Model SelectionSpuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection
Deep neural networks have exhibited remarkable performance in various domains. However, the reliance of these models on spurious features has raised concerns about their reliability. A promising solution to this problem …
Objectobject-detectionObject DetectionOpen-vocabulary object detection+1On the Unreasonable Effectiveness of Last-layer Retraining
Last-layer retraining (LLR) methods -- wherein the last layer of a neural network is reinitialized and retrained on a held-out set following ERM training -- have garnered interest as an efficient approach to rectify depe…