# Simple Disentanglement of Style and Content in Visual Representations Source: [Simple Disentanglement of Style and Content in Visual Representations]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:23:26.146Z Authors: Lilian Ngweta, Subha Maity, Alex Gittens, Yuekai Sun, Mikhail Yurochkin Published: 2023-02-20T06:48:19.000Z ## Abstract Learning visual representations with interpretable features, i.e., disentangled representations, remains a challenging problem. Existing methods demonstrate some success but are hard to apply to large-scale vision datasets like ImageNet. In this work, we propose a simple post-processing framework to disentangle content and style in learned representations from pre-trained vision models. We model the pre-trained features probabilistically as linearly entangled combinations of the latent content and style factors and develop a simple disentanglement algorithm based on the probabilistic model. We show that the method provably disentangles content and style features and verify its efficacy empirically. Our post-processed features yield significant domain generalization performance improvements when the distribution shift occurs due to style changes or style-related spurious correlations. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()