paper-with-me

Papers

Cross-Iteration Batch Normalization

2020-02-13 · CVPR 2021 1 · Zhuliang Yao, Yue Cao, Shuxin Zheng, Gao Huang, Stephen Lin

A well-known issue of Batch Normalization is its significantly reduced effectiveness in the case of small mini-batch sizes. When a mini-batch contains few examples, the statistics upon which the normalization is defined cannot be reliably estimated from it during a training iteration. To address this problem, we present Cross-Iteration Batch Normalization (CBN), in which examples from multiple recent iterations are jointly utilized to enhance estimation quality. A challenge of computing statistics over multiple iterations is that the network activations from different iterations are not comparable to each other due to changes in network weights. We thus compensate for the network weight changes via a proposed technique based on Taylor polynomials, so that the statistics can be accurately estimated and batch normalization can be effectively applied. On object detection and image classification with small mini-batch sizes, CBN is found to outperform the original batch normalization and a direct calculation of statistics over previous iterations without the proposed compensation technique. Code is available at https://github.com/Howal/Cross-iterationBatchNorm .

📄 PDF Abstract BibTeX arXiv:2002.05712

Code (2)

Howal/Cross-iterationBatchNorm 공식 구현 pytorch
hlld/cross-iteration-batch_normalization tf

Tasks

image-classificationImage Classificationobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
Residual Connection 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

Batch Group Normalization

2020-12-04 · Xiao-Yun Zhou, Jiacheng Sun, Nanyang Ye, Xu Lan 외

Deep Convolutional Neural Networks (DCNNs) are hard and time-consuming to train. Normalization is one of the effective solutions. Among previous normalization methods, Batch Normalization (BN) performs well at medium and…

Domain AdaptationFew-Shot LearningGPUimage-classification+3

Patch-aware Batch Normalization for Improving Cross-domain Robustness

2023-04-06 · Lei Qi, Dongjia Zhao, Yinghuan Shi, Xin Geng

Despite the significant success of deep learning in computer vision tasks, cross-domain tasks still present a challenge in which the model's performance will degrade when the training set and the test set follow differen…

Data Augmentationobject-detectionObject DetectionRetrieval+1

Iterative Normalization: Beyond Standardization towards Efficient Whitening

2019-04-06 · CVPR 2019 6 · Lei Huang, Yi Zhou, Fan Zhu, Li Liu 외

Batch Normalization (BN) is ubiquitously employed for accelerating neural network training and improving the generalization capability by performing standardization within mini-batches. Decorrelated Batch Normalization (…

Robust Object Detection

Batch Normalization Sampling

2018-10-25 · Zhaodong Chen, Lei Deng, Guoqi Li, Jiawei Sun 외

Deep Neural Networks (DNNs) thrive in recent years in which Batch Normalization (BN) plays an indispensable role. However, it has been observed that BN is costly due to the reduction operations. In this paper, we propose…

Computational EfficiencyGPU

Rethinking Normalization Methods in Federated Learning

2022-10-07 · Zhixu Du, Jingwei Sun, Ang Li, Pin-Yu Chen 외

Federated learning (FL) is a popular distributed learning framework that can reduce privacy risks by not explicitly sharing private data. In this work, we explicitly uncover external covariate shift problem in FL, which …

Federated Learning