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
  • [31] Decoupling MaxLogit for Out-of-Distribution Detection
    Zhang, Zihan
    Xiang, Xiang
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, : 3388 - 3397
  • [32] Exploring the Limits of Out-of-Distribution Detection
    Fort, Stanislav
    Ren, Jie
    Lakshminarayanan, Balaji
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [33] Likelihood Ratios for Out-of-Distribution Detection
    Ren, Jie
    Liu, Peter J.
    Fertig, Emily
    Snoek, Jasper
    Poplin, Ryan
    DePristo, Mark A.
    Dillon, Joshua V.
    Lakshminarayanan, Balaji
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [34] Semantically Coherent Out-of-Distribution Detection
    Yang, Jingkang
    Wang, Haoqi
    Feng, Litong
    Yan, Xiaopeng
    Zheng, Huabin
    Zhang, Wayne
    Liub, Ziwei
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 8281 - 8289
  • [35] Generalized Out-of-Distribution Detection: A Survey
    Yang, Jingkang
    Zhou, Kaiyang
    Li, Yixuan
    Liu, Ziwei
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2024, : 5635 - 5662
  • [36] Semantic enhanced for out-of-distribution detection
    Jiang, Weijie
    Yu, Yuanlong
    FRONTIERS IN NEUROROBOTICS, 2022, 16
  • [37] Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data
    Grcic, Matej
    Bevandic, Petra
    Kalafatic, Zoran
    Segvic, Sinisa
    SENSORS, 2024, 24 (04)
  • [38] Class-Incremental Gesture Recognition Learning with Out-of-Distribution Detection
    Li, Mingxue
    Cong, Yang
    Liu, Yuyang
    Sun, Gan
    2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2022, : 1503 - 1508
  • [39] Topological Structure Learning forWeakly-Supervised Out-of-Distribution Detection
    He, Rundong
    Li, Rongxue
    Han, Zhongyi
    Yang, Xihong
    Yin, Yilong
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 4858 - 4866
  • [40] GraphDE: A Generative Framework for Debiased Learning and Out-of-Distribution Detection on Graphs
    Li, Zenan
    Wu, Qitian
    Nie, Fan
    Yan, Junchi
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,