Glocal Energy-based Learning for Few-Shot Open-Set Recognition

Publication Name

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Abstract

Few-shot open-set recognition (FSOR) is a challenging task of great practical value. It aims to categorize a sample to one of the predefined, closed-set classes illustrated by few examples while being able to reject the sample from unknown classes. In this work, we approach the FSOR task by proposing a novel energy-based hybrid model. The model is composed of two branches, where a classification branch learns a metric to classify a sample to one of closed-set classes and the energy branch explicitly estimates the open-set probability. To achieve holistic detection of open-set samples, our model leverages both class-wise and pixel-wise features to learn a glocal energy-based score, in which a global energy score is learned using the class-wise features, while a local energy score is learned using the pixel-wise features. The model is enforced to assign large energy scores to samples that are deviated from the few-shot examples in either the class-wise features or the pixel-wise features, and to assign small energy scores otherwise. Experiments on three standard FSOR datasets show the superior performance of our model.11Code is available at https://github.com/00why00/Glocal

Open Access Status

This publication may be available as open access

Volume

2023-June

First Page

7507

Last Page

7516

Funding Number

DP220101784

Funding Sponsor

Australian Research Council

Share

COinS
 

Link to publisher version (DOI)

http://dx.doi.org/10.1109/CVPR52729.2023.00725