Robust Novelty Detection through Style-Conscious Feature Ranking
This addresses robust novelty detection for machine learning systems by mitigating spurious correlations from style changes, though it is incremental as it builds on domain generalization literature.
The paper tackles the problem of novelty detection by distinguishing between task-relevant semantic changes and irrelevant style changes, introducing Stylist to discard environment-biased features, which improves performance across diverse datasets with stylistic and content shifts.
Novelty detection seeks to identify samples deviating from a known distribution, yet data shifts in a multitude of ways, and only a few consist of relevant changes. Aligned with out-of-distribution generalization literature, we advocate for a formal distinction between task-relevant semantic or content changes and irrelevant style changes. This distinction forms the basis for robust novelty detection, emphasizing the identification of semantic changes resilient to style distributional shifts. To this end, we introduce Stylist, a method that utilizes pretrained large-scale model representations to selectively discard environment-biased features. By computing per-feature scores based on feature distribution distances between environments, Stylist effectively eliminates features responsible for spurious correlations, enhancing novelty detection performance. Evaluations on adapted domain generalization datasets and a synthetic dataset demonstrate Stylist's efficacy in improving novelty detection across diverse datasets with stylistic and content shifts. The code is available at https://github.com/bit-ml/Stylist.