A Batch Normalization Classifier for Domain Adaptation

03/22/2021
by   Matthew R. Behrend, et al.
0

Adapting a model to perform well on unforeseen data outside its training set is a common problem that continues to motivate new approaches. We demonstrate that application of batch normalization in the output layer, prior to softmax activation, results in improved generalization across visual data domains in a refined ResNet model. The approach adds negligible computational complexity yet outperforms many domain adaptation methods that explicitly learn to align data domains. We benchmark this technique on the Office-Home dataset and show that batch normalization is competitive with other leading methods. We show that this method is not sensitive to presence of source data during adaptation and further present the impact on trained tensor distributions tends toward sparsity. Code is available at https://github.com/matthewbehrend/BNC

READ FULL TEXT
research
12/20/2021

Reciprocal Normalization for Domain Adaptation

Batch normalization (BN) is widely used in modern deep neural networks, ...
research
06/07/2023

Normalization Layers Are All That Sharpness-Aware Minimization Needs

Sharpness-aware minimization (SAM) was proposed to reduce sharpness of m...
research
01/19/2021

Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics

In this paper, we propose a novel domain adaptation method for the sourc...
research
01/04/2020

Adversarial-Learned Loss for Domain Adaptation

Recently, remarkable progress has been made in learning transferable rep...
research
08/26/2023

Generalized Lightness Adaptation with Channel Selective Normalization

Lightness adaptation is vital to the success of image processing to avoi...
research
03/25/2021

Universal Representation Learning from Multiple Domains for Few-shot Classification

In this paper, we look at the problem of few-shot classification that ai...
research
11/28/2020

Batch Normalization with Enhanced Linear Transformation

Batch normalization (BN) is a fundamental unit in modern deep networks, ...

Please sign up or login with your details

Forgot password? Click here to reset