paper-with-me

Papers

Continual Normalization: Rethinking Batch Normalization for Online Continual Learning

2022-03-30 · ICLR 2022 4 · Quang Pham, Chenghao Liu, Steven Hoi

Existing continual learning methods use Batch Normalization (BN) to facilitate training and improve generalization across tasks. However, the non-i.i.d and non-stationary nature of continual learning data, especially in the online setting, amplify the discrepancy between training and testing in BN and hinder the performance of older tasks. In this work, we study the cross-task normalization effect of BN in online continual learning where BN normalizes the testing data using moments biased towards the current task, resulting in higher catastrophic forgetting. This limitation motivates us to propose a simple yet effective method that we call Continual Normalization (CN) to facilitate training similar to BN while mitigating its negative effect. Extensive experiments on different continual learning algorithms and online scenarios show that CN is a direct replacement for BN and can provide substantial performance improvements. Our implementation is available at \url{https://github.com/phquang/Continual-Normalization}.

📄 PDF Abstract BibTeX arXiv:2203.16102

Code (1)

phquang/continual-normalization 공식 구현 pytorch

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Rethinking Normalization and Elimination Singularity in Neural Networks

2019-11-21 · Siyuan Qiao, Huiyu Wang, Chenxi Liu, Wei Shen 외

In this paper, we study normalization methods for neural networks from the perspective of elimination singularity. Elimination singularities correspond to the points on the training trajectory where neurons become consis…

image-classificationImage ClassificationInstance Segmentationobject-detection+3

TaskNorm: Rethinking Batch Normalization for Meta-Learning

2020-03-06 · ICML 2020 1 · John Bronskill, Jonathan Gordon, James Requeima, Sebastian Nowozin 외

Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential component of meta-learning pipelines. However, …

General Classificationimage-classificationImage ClassificationMeta-Learning

New Insights for the Stability-Plasticity Dilemma in Online Continual Learning

2023-02-17 · Dahuin Jung, Dongjin Lee, Sunwon Hong, Hyemi Jang 외

The aim of continual learning is to learn new tasks continuously (i.e., plasticity) without forgetting previously learned knowledge from old tasks (i.e., stability). In the scenario of online continual learning, wherein …

Continual Learning

Online Normalization for Training Neural Networks

2019-05-15 · NeurIPS 2019 12 · Vitaliy Chiley, Ilya Sharapov, Atli Kosson, Urs Koster 외

Online Normalization is a new technique for normalizing the hidden activations of a neural network. Like Batch Normalization, it normalizes the sample dimension. While Online Normalization does not use batches, it is as …

General Classificationimage-classificationImage ClassificationImage Segmentation+3

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