Differentiable Learning-to-Normalize via Switchable NormalizationDownload PDF

Published: 21 Dec 2018, Last Modified: 21 Apr 2024ICLR 2019 Conference Blind SubmissionReaders: Everyone
Abstract: We address a learning-to-normalize problem by proposing Switchable Normalization (SN), which learns to select different normalizers for different normalization layers of a deep neural network. SN employs three distinct scopes to compute statistics (means and variances) including a channel, a layer, and a minibatch. SN switches between them by learning their importance weights in an end-to-end manner. It has several good properties. First, it adapts to various network architectures and tasks (see Fig.1). Second, it is robust to a wide range of batch sizes, maintaining high performance even when small minibatch is presented (e.g. 2 images/GPU). Third, SN does not have sensitive hyper-parameter, unlike group normalization that searches the number of groups as a hyper-parameter. Without bells and whistles, SN outperforms its counterparts on various challenging benchmarks, such as ImageNet, COCO, CityScapes, ADE20K, and Kinetics. Analyses of SN are also presented. We hope SN will help ease the usage and understand the normalization techniques in deep learning. The code of SN will be released.
Keywords: normalization, deep learning, CNN, computer vision
Code: [![Papers with Code](/images/pwc_icon.svg) 3 community implementations](https://paperswithcode.com/paper/?openreview=ryggIs0cYQ)
Data: [ADE20K](https://paperswithcode.com/dataset/ade20k), [COCO](https://paperswithcode.com/dataset/coco), [Cityscapes](https://paperswithcode.com/dataset/cityscapes), [ImageNet](https://paperswithcode.com/dataset/imagenet), [Kinetics](https://paperswithcode.com/dataset/kinetics)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 7 code implementations](https://www.catalyzex.com/paper/arxiv:1806.10779/code)
7 Replies