paper-with-me

Papers

Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs

2020-02-29 · ICLR 2021 1 · Jonathan Frankle, David J. Schwab, Ari S. Morcos

A wide variety of deep learning techniques from style transfer to multitask learning rely on training affine transformations of features. Most prominent among these is the popular feature normalization technique BatchNorm, which normalizes activations and then subsequently applies a learned affine transform. In this paper, we aim to understand the role and expressive power of affine parameters used to transform features in this way. To isolate the contribution of these parameters from that of the learned features they transform, we investigate the performance achieved when training only these parameters in BatchNorm and freezing all weights at their random initializations. Doing so leads to surprisingly high performance considering the significant limitations that this style of training imposes. For example, sufficiently deep ResNets reach 82% (CIFAR-10) and 32% (ImageNet, top-5) accuracy in this configuration, far higher than when training an equivalent number of randomly chosen parameters elsewhere in the network. BatchNorm achieves this performance in part by naturally learning to disable around a third of the random features. Not only do these results highlight the expressive power of affine parameters in deep learning, but - in a broader sense - they characterize the expressive power of neural networks constructed simply by shifting and rescaling random features.

📄 PDF Abstract BibTeX arXiv:2003.00152

Code (4)

facebookresearch/open_lth pytorch
sayakpaul/Training-BatchNorm-and-Only-BatchNorm
wandb/awesome-dl-projects tf
wandb/gallery tf

Tasks

Style Transfer

Methods 이 논문이 사용한 방법론

Average Pooling 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,…
Batch Normalization 설명 없음
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

Training BatchNorm Only in Neural Architecture Search and Beyond

2021-12-01 · Yichen Zhu, Jie Du, Yuqin Zhu, Yi Wang 외

This work investigates the usage of batch normalization in neural architecture search (NAS). Specifically, Frankle et al. find that training BatchNorm only can achieve nontrivial performance. Furthermore, Chen et al. cla…

FairnessNeural Architecture Search

Does Data Augmentation Benefit from Split BatchNorms

2020-10-15 · Amil Merchant, Barret Zoph, Ekin Dogus Cubuk

Data augmentation has emerged as a powerful technique for improving the performance of deep neural networks and led to state-of-the-art results in computer vision. However, state-of-the-art data augmentation strongly dis…

Data Augmentationimage-classificationImage Classification

An Empirical Analysis of the Shift and Scale Parameters in BatchNorm

2023-03-22 · Yashna Peerthum, Mark Stamp

Batch Normalization (BatchNorm) is a technique that improves the training of deep neural networks, especially Convolutional Neural Networks (CNN). It has been empirically demonstrated that BatchNorm increases performance…

Separating the Effects of Batch Normalization on CNN Training Speed and Stability Using Classical Adaptive Filter Theory

2020-02-25 · Elaina Chai, Mert Pilanci, Boris Murmann

Batch Normalization (BatchNorm) is commonly used in Convolutional Neural Networks (CNNs) to improve training speed and stability. However, there is still limited consensus on why this technique is effective. This paper u…

Towards an Adversarially Robust Normalization Approach

2020-06-19 · Muhammad Awais, Fahad Shamshad, Sung-Ho Bae

Batch Normalization (BatchNorm) is effective for improving the performance and accelerating the training of deep neural networks. However, it has also shown to be a cause of adversarial vulnerability, i.e., networks with…