# Adversarial Dependence Minimization Source: [Adversarial Dependence Minimization]() Collection index: [llms.txt]() Data updated: 2026-06-20T05:00:13.953Z Authors: Pierre-Fran\\c{c}ois De Plaen, Tinne Tuytelaars, Marc Proesmans, Luc Van Gool Published: 2025-02-05T14:43:40.000Z ## Abstract Minimally redundant representations are typically learned by minimizing feature covariance. However, covariance-based methods fail to eliminate all dependencies/redundancies, as linearly uncorrelated variables can still exhibit nonlinear relationships. To address this, we introduce ADM, a differentiable algorithm that minimizes statistical dependence between feature dimensions through an adversarial game: auxiliary networks identify dependencies, while the encoder removes them. We prove that mutual independence is achieved at the global optimum, empirically verify convergence, and study three potential applications: extending PCA to nonlinear decorrelation, improving generalization in image classification, and preventing dimensional collapse in self-supervised learning. By promoting statistically independent representations, ADM paves the way for learning more robust, compressed, and generalizable representations across diverse applications. ## 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. - [Image Classification on ImageNet-1k (Accuracy and dCor^2)](): Image Classification; ImageNet-1K; Accuracy: 65.3. ## Original sources and implementation [Original paper]() [PDF]()