paper-with-me

홈 › Papers

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

2022-04-06 · Polina Kirichenko, Pavel Izmailov, Andrew Gordon Wilson

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.

📄 PDF Abstract BibTeX arXiv:2204.02937

Code (4)

polinakirichenko/deep_feature_reweighting 공식 구현 pytorch
facebookresearch/Whac-A-Mole pytorch
lfhase/feat pytorch
ywolfeee/freeze-then-train pytorch

Tasks

GPUOut-of-Distribution Generalization

Similar Papers 제목 키워드 기반

Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?

2023-08-01 · Phuong Quynh Le, Jörg Schlötterer, Christin Seifert

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

2023-12-08 · Mahdi Ghaznavi, Hesam Asadollahzadeh, HamidReza Yaghoubi Araghi, Fahimeh Hosseini Noohdani 외

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 Classification

Towards Last-layer Retraining for Group Robustness with Fewer Annotations

2023-09-15 · NeurIPS 2023 11 · Tyler LaBonte, Vidya Muthukumar, Abhishek Kumar

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 Selection

Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection

2023-10-31 · Mohammad Azizmalayeri, Reza Abbasi, Amir Hosein Haji Mohammad rezaie, Reihaneh Zohrabi 외

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+1

On the Unreasonable Effectiveness of Last-layer Retraining

2025-12-01 · John C. Hill, Tyler LaBonte, Xinchen Zhang, Vidya Muthukumar arxiv

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…