While deep learning models have shown remarkable performance in various tasks, they are susceptible to learning non-generalizable _spurious features_ rather than the core features that are genuinely correlated to the true label. In this paper, beyond existing analyses of linear models, we theoretically examine the learning process of a two-layer nonlinear convolutional neural network in the presence of spurious features. Our analysis suggests that imbalanced data groups and easily learnable spurious features can lead to the dominance of spurious features during the learning process. In light of this, we propose a new training algorithm called **PDE** that efficiently enhances the model's robustness for a better worst-group performance. PDE begins with a group-balanced subset of training data and progressively expands it to facilitate the learning of the core features. Experiments on synthetic and real-world benchmark datasets confirm the superior performance of our method on models such as ResNets and Transformers. On average, our method achieves a $2.8$ \% improvement in worst-group accuracy compared with the state-of-the-art method, while enjoying up to $10\times$ faster training efficiency.

To remedy this, most robust fine-tuning methods aim to preserve the pre-trained features.

Results averaged over ResNet18 and ResNet50.

This procedure is called Deep Feature Reweighting (DFR).

Shortcuts, spurious rules that perform well during training but fail to generalize, present a major challenge to the reliability of deep networks (Geirhos et al., 2020). However, the impact of shortcuts on feature representations remains understudied, obstructing the design of principled shortcut-mitigation methods. To overcome this limitation, we investigate the layer-wise localization of shortcuts in deep models. Our novel experiment design quantifies the layer-wise contribution to accuracy degradation caused by a shortcut-inducing skew by counterfactual training on clean and skewed datasets. We employ our design to study shortcuts on CIFAR-10, Waterbirds, and CelebA datasets across VGG, ResNet, DeiT, and ConvNeXt architectures. We find that shortcut learning is not localized in specific layers but distributed throughout the network. Different network parts play different roles in this process: shallow layers predominantly encode spurious features, while deeper layers predominantly forget core features that are predictive on clean data. We also analyze the differences in localization and describe its principal axes of variation. Finally, our analysis of layer-wise shortcut-mitigation strategies suggests the hardness of designing general methods, supporting dataset- and architecture-specific approaches instead.