Learning Robust Representations by Projecting Superficial Statistics Out

TL;DR

This paper introduces techniques to improve deep neural networks' robustness to distribution shifts by removing superficial statistical cues, leading to better generalization across unseen domains without needing target domain data.

Contribution

The paper proposes novel methods that use GLCM to identify and suppress superficial texture cues, enhancing domain generalization in neural networks.

Findings

Achieves comparable or better performance than existing domain generalization methods.

Effectively reduces reliance on superficial statistics like texture.

Improves out-of-sample generalization across multiple datasets.

Abstract

Despite impressive performance as evaluated on i.i.d. holdout data, deep neural networks depend heavily on superficial statistics of the training data and are liable to break under distribution shift. For example, subtle changes to the background or texture of an image can break a seemingly powerful classifier. Building on previous work on domain generalization, we hope to produce a classifier that will generalize to previously unseen domains, even when domain identifiers are not available during training. This setting is challenging because the model may extract many distribution-specific (superficial) signals together with distribution-agnostic (semantic) signals. To overcome this challenge, we incorporate the gray-level co-occurrence matrix (GLCM) to extract patterns that our prior knowledge suggests are superficial: they are sensitive to the texture but unable to capture the gestalt of an image. Then we introduce two techniques for improving our networks' out-of-sample performance. The first method is built on the reverse gradient method that pushes our model to learn representations from which the GLCM representation is not predictable. The second method is built on the independence introduced by projecting the model's representation onto the subspace orthogonal to GLCM representation's. We test our method on the battery of standard domain generalization data sets and, interestingly, achieve comparable or better performance as compared to other domain generalization methods that explicitly require samples from the target distribution for training.