# Mode Normalization Source: [Mode Normalization]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:14:52.998Z Authors: Lucas Deecke, Iain Murray, Hakan Bilen Published: 2018-10-12T12:10:10.000Z ## Abstract Normalization methods are a central building block in the deep learning toolbox. They accelerate and stabilize training, while decreasing the dependence on manually tuned learning rate schedules. When learning from multi-modal distributions, the effectiveness of batch normalization (BN), arguably the most prominent normalization method, is reduced. As a remedy, we propose a more flexible approach: by extending the normalization to more than a single mean and variance, we detect modes of data on-the-fly, jointly normalizing samples that share common features. We demonstrate that our method outperforms BN and other widely used normalization techniques in several experiments, including single and multi-task datasets. ## 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 CIFAR-10 1.0 (test) (Adversarial Robustness)](): Image Classification; CIFAR-10 1.0 (test); Clean Accuracy: 83.28. ## Original sources and implementation [Original paper]() [PDF]()