Deep Neural Network Models Trained With A Fixed Random Classifier Transfer Better Across Domains
Abstract
The recently discovered Neural collapse (NC) phenomenon states that the last-layer weights of Deep Neural Networks (DNN), converge to the so-called Equiangular Tight Frame (ETF) simplex, at the terminal phase of their training. This ETF geometry is equivalent to vanishing within-class variability of the last layer activations. Inspired by NC properties, we explore in this paper the transferability of DNN models trained with their last layer weight fixed according to ETF. This enforces class separation by eliminating class covariance information, effectively providing implicit regularization. We show that DNN models trained with such a fixed classifier significantly improve transfer performance, particularly on out-of-domain datasets. On a broad range of fine-grained image classification datasets, our approach outperforms i) baseline methods that do not perform any covariance regularization (up to 22%), as well as ii) methods that explicitly whiten covariance of activations throughout training (up to 19%). Our findings suggest that DNNs trained with fixed ETF classifiers offer a powerful mechanism for improving transfer learning across domains.
Cite
@article{arxiv.2402.18614,
title = {Deep Neural Network Models Trained With A Fixed Random Classifier Transfer Better Across Domains},
author = {Hafiz Tiomoko Ali and Umberto Michieli and Ji Joong Moon and Daehyun Kim and Mete Ozay},
journal= {arXiv preprint arXiv:2402.18614},
year = {2024}
}
Comments
ICASSP 2024. Copyright 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other