Home/Growing a Brain: Fine-Tuning by Increasing Model Capacity

Growing a Brain: Fine-Tuning by Increasing Model Capacity

Yuxiong Wang, Deva Ramanan, Martial Hebert
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), July, 2017

Download: Adobe portable document format (PDF)

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

CNNs have made an undeniable impact on computer vision through the ability to learn high-capacity models with large annotated training sets. One of their remarkable properties is the ability to transfer knowledge from a large source dataset to a (typically smaller) target dataset. This is usually accomplished through fine-tuning a fixed-size network on new target data. Indeed, virtually every contemporary visual recognition system makes use of fine-tuning to transfer knowledge from ImageNet. In this work, we analyze what components and parameters change during fine-tuning, and discover that increasing model capacity allows for more natural model adaptation through fine-tuning. By making an analogy to developmental learning, we demonstrate that “growing” a CNN with additional units, either by widening existing layers or deepening the overall network, significantly outperforms classic fine-tuning approaches. But in order to properly grow a network, we show that newly-added units must be appropriately normalized to allow for a pace of learning that is consistent with existing units. We empirically validate our approach on several benchmark datasets, producing state-of-the-art results.

BibTeX Reference
@conference{Wang–2017–26053,
title = {Growing a Brain: Fine-Tuning by Increasing Model Capacity},
author = {Yuxiong Wang and Deva Ramanan and Martial Hebert},
booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017},
}
2017-06-23T09:08:07+00:00