# Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting

arXiv: https://arxiv.org/abs/2409.14637 · HTML: https://mlsanity.com/paper/2409.14637/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 23 Sep 2024.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [A Survey on Deep Transfer Learning](https://mlsanity.com/paper/1808.01974/) (2018)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [Counterfactual Samples Synthesizing for Robust Visual Question Answering](https://mlsanity.com/paper/2003.06576/) (2020)
- [Understanding the Failure Modes of Out-of-Distribution Generalization](https://mlsanity.com/paper/2010.15775/) (2020)
- [On Feature Learning in the Presence of Spurious Correlations](https://mlsanity.com/paper/2210.11369/) (2022)
- [Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing](https://mlsanity.com/paper/1912.07538/) (2019)
- [Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning](https://mlsanity.com/paper/2201.03529/) (2022)
- [MEDFAIR: Benchmarking Fairness for Medical Imaging](https://mlsanity.com/paper/2210.01725/) (2022)
- [Simple and Fast Group Robustness by Automatic Feature Reweighting](https://mlsanity.com/paper/2306.11074/) (2023)
- [Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentation](https://mlsanity.com/paper/1812.06707/) (2018)

## Built on by (most cited first, 3 of 3)

- [FairDropout: Using Example-Tied Dropout to Enhance Generalization of Minority Groups](https://mlsanity.com/paper/2502.06695/) (2025)
- [Test Time Adaptation Using Adaptive Quantile Recalibration](https://mlsanity.com/paper/2511.03148/) (2025)
- [BAT: Better Audio Transformer Guided by Convex Gated Probing](https://mlsanity.com/paper/2602.16305/) (2026)

## Abstract (arXiv)

Spurious correlations are a major source of errors for machine learning models, in particular when aiming for group-level fairness. It has been recently shown that a powerful approach to combat spurious correlations is to re-train the last layer on a balanced validation dataset, isolating robust features for the predictor. However, key attributes can sometimes be discarded by neural networks towards the last layer. In this work, we thus consider retraining a classifier on a set of features derived from all layers. We utilize a recently proposed feature selection strategy to select unbiased features from all the layers. We observe this approach gives significant improvements in worst-group accuracy on several standard benchmarks.