# LocalNorm: Robust Image Classification through Dynamically Regularized Normalization Source: [LocalNorm: Robust Image Classification through Dynamically Regularized Normalization]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:38.157Z Authors: Bojian Yin, Siebren Schaafsma, Henk Corporaal, H. Steven Scholte, Sander M. Bohte Published: 2019-02-18T12:58:23.000Z ## Abstract While modern convolutional neural networks achieve outstanding accuracy on many image classification tasks, they are, compared to humans, much more sensitive to image degradation. Here, we describe a variant of Batch Normalization, LocalNorm, that regularizes the normalization layer in the spirit of Dropout while dynamically adapting to the local image intensity and contrast at test-time. We show that the resulting deep neural networks are much more resistant to noise-induced image degradation, improving accuracy by up to three times, while achieving the same or slightly better accuracy on non-degraded classical benchmarks. In computational terms, LocalNorm adds negligible training cost and little or no cost at inference time, and can be applied to already-trained networks in a straightforward manner. ## 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]()