Learning compositional representations for few-shot recognition

October 2019

Learning compositional representations for few-shot recognition

Authors:

Pavel Tokmakov, Yuxiong Wang, and Martial Hebert
Conference Paper
Proceedings of (ICCV) International Conference on Computer Vision

Abstract:

One of the key limitations of modern deep learning approaches lies in the amount of data required to train them. Humans, by contrast, can learn to recognize novel categories from just a few examples. Instrumental to this rapid learning ability is the compositional structure of concept representations in the human brain --- something that deep learning models are lacking. In this work, we make a step towards bridging this gap between human and machine learning by introducing a simple regularization technique that allows the learned representation to be decomposable into parts. Our method uses category-level attribute annotations to disentangle the feature space of a network into subspaces corresponding to the attributes. These attributes can be either purely visual, like object parts, or more abstract, like openness and symmetry. We demonstrate the value of compositional representations on three datasets: CUB-200-2011, SUN397, and ImageNet, and show that they require fewer examples to learn classifiers for novel categories.
@conference{Tokmakov-2019-122545,
author = {Pavel Tokmakov And Yuxiong Wang And Martial Hebert},
title = {Learning compositional representations for few-shot recognition},
booktitle = {Proceedings of (ICCV) International Conference on Computer Vision},
year = {2019},
month = {October},
pages = {6371 - 6380},
}
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.