Out-Of-Distribution Detection In Unsupervised Continual Learning

被引:2
|
作者
He, Jiangpeng [1 ]
Zhu, Fengqing [1 ]
机构
[1] Purdue Univ, Elmore Family Sch Elect & Comp Engn, W Lafayette, IN 47907 USA
关键词
D O I
10.1109/CVPRW56347.2022.00430
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Unsupervised continual learning aims to learn new tasks incrementally without requiring human annotations. However, most existing methods, especially those targeted on image classification, only work in a simplified scenario by assuming all new data belong to new tasks, which is not realistic if the class labels are not provided. Therefore, to perform unsupervised continual learning in real life applications, an out-of-distribution detector is required at beginning to identify whether each new data corresponds to a new task or already learned tasks, which still remains under-explored yet. In this work, we formulate the problem for Out-of-distribution Detection in Unsupervised Continual Learning (OOD-UCL) with the corresponding evaluation protocol. In addition, we propose a novel OOD detection method by correcting the output bias at first and then enhancing the output confidence for in-distribution data based on task discriminativeness, which can be applied directly without modifying the learning procedures and objectives of continual learning. Our method is evaluated on CIFAR-100 dataset by following the proposed evaluation protocol and we show improved performance compared with existing OOD detection methods under the unsupervised continual learning scenario.
引用
收藏
页码:3849 / 3854
页数:6
相关论文
共 50 条
  • [21] Is Out-of-Distribution Detection Learnable?
    Fang, Zhen
    Li, Yixuan
    Lu, Jie
    Dong, Jiahua
    Han, Bo
    Liu, Feng
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [22] Self-Supervised Learning for Generalizable Out-of-Distribution Detection
    Mohseni, Sina
    Pitale, Mandar
    Yadawa, J. B. S.
    Wang, Zhangyang
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 5216 - 5223
  • [23] Improving Out-of-Distribution Detection by Learning From the Deployment Environment
    Inkawhich, Nathan
    Zhang, Jingyang
    Davis, Eric K.
    Luley, Ryan
    Chen, Yiran
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 : 2070 - 2086
  • [24] Out-of-Distribution (OOD) Detection Based on Deep Learning: A Review
    Cui, Peng
    Wang, Jinjia
    ELECTRONICS, 2022, 11 (21)
  • [25] Improving Out-of-Distribution Detection by Learning from the Deployment Environment
    Inkawhich, Nathan
    Zhang, Jingyang
    Davis, Eric K.
    Luley, Ryan
    Chen, Yiran
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15 : 2070 - 2086
  • [26] On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code
    Weyssow, Martin
    Zhou, Xin
    Kim, Kisub
    Lo, David
    Sahraoui, Houari
    PROCEEDINGS OF THE 31ST ACM JOINT MEETING EUROPEAN SOFTWARE ENGINEERING CONFERENCE AND SYMPOSIUM ON THE FOUNDATIONS OF SOFTWARE ENGINEERING, ESEC/FSE 2023, 2023, : 1470 - 1482
  • [27] SS3D: Unsupervised Out-of-Distribution Detection and Localization for Medical Volumes
    Doorenbos, Lars
    Sznitman, Raphael
    Marquez-Neila, Pablo
    BIOMEDICAL IMAGE REGISTRATION, DOMAIN GENERALISATION AND OUT-OF-DISTRIBUTION ANALYSIS, 2022, 13166 : 111 - 118
  • [28] Out-of-Distribution Detection for Automotive Perception
    Nitsch, Julia
    Itkina, Masha
    Senanayake, Ransalu
    Nieto, Juan
    Schmidt, Max
    Siegwart, Roland
    Kochenderfer, Mykel J.
    Cadena, Cesar
    2021 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), 2021, : 2938 - 2943
  • [29] Robust Cough Detection With Out-of-Distribution Detection
    Chen, Yuhan
    Attri, Pankaj
    Barahona, Jeffrey
    Hernandez, Michelle L.
    Carpenter, Delesha
    Bozkurt, Alper
    Lobaton, Edgar
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2023, 27 (07) : 3210 - 3221
  • [30] Learning on Graphs with Out-of-Distribution Nodes
    Song, Yu
    Wang, Donglin
    PROCEEDINGS OF THE 28TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2022, 2022, : 1635 - 1645