Out-Of-Distribution Detection In Unsupervised Continual Learning

被引:3
|
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] Entropic Out-of-Distribution Detection
    Macedo, David
    Ren, Tsang Ing
    Zanchettin, Cleber
    Oliveira, Adriano L., I
    Ludermir, Teresa
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [22] Watermarking for Out-of-distribution Detection
    Wang, Qizhou
    Liu, Feng
    Zhang, Yonggang
    Zhang, Jing
    Gong, Chen
    Liu, Tongliang
    Han, Bo
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [23] 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,
  • [24] On the Learnability of Out-of-distribution Detection
    Fang, Zhen
    Li, Yixuan
    Liu, Feng
    Han, Bo
    Lu, Jie
    JOURNAL OF MACHINE LEARNING RESEARCH, 2024, 25
  • [25] 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
  • [26] Out-of-Distribution (OOD) Detection Based on Deep Learning: A Review
    Cui, Peng
    Wang, Jinjia
    ELECTRONICS, 2022, 11 (21)
  • [27] 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
  • [28] 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
  • [29] Out-of-Distribution Detection via outlier exposure in federated learning
    Jeong, Gu-Bon
    Choi, Dong-Wan
    NEURAL NETWORKS, 2025, 185
  • [30] 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