Glocal energy-based learning for few-shot open-set recognition

• Main Authors: WANG, Haoyu, PANG, Guansong, WANG, Peng, ZHANG, Lei, WEI, Wei, ZHANG, Yanning
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Databases and Information Systems; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/8005; https://ink.library.smu.edu.sg/context/sis_research/article/9008/viewcontent/Wang_Glocal_Energy_Based_Learning_for_Few_Shot_Open_Set_Recognition_CVPR_2023_paper.pdf
• Institution: Singapore Management University

Few-shot open-set recognition (FSOR) is a challenging task of great practical value. It aims to categorize a sample to one of the pre-defined, 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 closedset classes and the energy branch explicitly estimates the open-set probability. To achieve holistic detection of openset samples, our model leverages both class-wise and pixelwise 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 pixelwise 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.