paper-with-me

Papers

Switchable Normalization for Learning-to-Normalize Deep Representation

2019-07-22 · Ping Luo, Ruimao Zhang, Jiamin Ren, Zhanglin Peng, Jingyu Li

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. 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, MegaFace, and Kinetics. Analyses of SN are also presented to answer the following three questions: (a) Is it useful to allow each normalization layer to select its own normalizer? (b) What impacts the choices of normalizers? (c) Do different tasks and datasets prefer different normalizers? We hope SN will help ease the usage and understand the normalization techniques in deep learning. The code of SN has been released at https://github.com/switchablenorms.

📄 PDF Abstract BibTeX arXiv:1907.10473

Code (0)

등록된 구현이 없습니다.

Tasks

GPU

Methods 이 논문이 사용한 방법론

Instance Normalization Instance Normalization (also known as contrast normalization) is a normalization layer where: $$ y_{tijk} = \frac{x_{tijk} - \mu_{ti}}{\sqrt{\sigma_{ti}^2 +…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Batch Normalization 설명 없음
Switchable Normalization 설명 없음
Group Normalization Group Normalization is a normalization layer that divides channels into groups and normalizes the features within each group. GN does not exploit the batch dimension, and its…

Similar Papers 제목 키워드 기반

Differentiable Learning-to-Normalize via Switchable Normalization

2018-06-28 · ICLR 2019 5 · Ping Luo, Jiamin Ren, Zhanglin Peng, Ruimao Zhang 외

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 s…

GPU

SSN: Learning Sparse Switchable Normalization via SparsestMax

2019-03-09 · CVPR 2019 6 · Wenqi Shao, Tianjian Meng, Jingyu Li, Ruimao Zhang 외

Normalization methods improve both optimization and generalization of ConvNets. To further boost performance, the recently-proposed switchable normalization (SN) provides a new perspective for deep learning: it learns to…

Do Normalization Layers in a Deep ConvNet Really Need to Be Distinct?

2018-11-19 · Ping Luo, Zhanglin Peng, Jiamin Ren, Ruimao Zhang

Yes, they do. This work investigates a perspective for deep learning: whether different normalization layers in a ConvNet require different normalizers. This is the first step towards understanding this phenomenon. We al…

Switchable Whitening for Deep Representation Learning

2019-04-22 · ICCV 2019 10 · Xingang Pan, Xiaohang Zhan, Jianping Shi, Xiaoou Tang 외

Normalization methods are essential components in convolutional neural networks (CNNs). They either standardize or whiten data using statistics estimated in predefined sets of pixels. Unlike existing works that design no…

Domain Adaptationimage-classificationImage ClassificationRepresentation Learning+3

Exemplar Normalization for Learning Deep Representation

2020-03-19 · CVPR 2020 6 · Ruimao Zhang, Zhanglin Peng, Lingyun Wu, Zhen Li 외

Normalization techniques are important in different advanced neural networks and different tasks. This work investigates a novel dynamic learning-to-normalize (L2N) problem by proposing Exemplar Normalization (EN), which…

Semantic Segmentation