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
  • [1] CONTINUAL LEARNING FOR OUT-OF-DISTRIBUTION PEDESTRIAN DETECTION
    Molahasani, Mahdiyar
    Etemad, Ali
    Greenspan, Michael
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 2685 - 2689
  • [2] Continual Evidential Deep Learning for Out-of-Distribution Detection
    Aguilar, Eduardo
    Raducanu, Bogdan
    Radeva, Petia
    De Weijer, Joost Van
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS, ICCVW, 2023, : 3436 - 3446
  • [3] Unsupervised evaluation for out-of-distribution detection
    Zhang, Yuhang
    Hu, Jiani
    Wen, Dongchao
    Deng, Weihong
    Pattern Recognition, 2025, 160
  • [4] Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
    Zheng, Haotian
    Wang, Qizhou
    Fang, Zhen
    Xia, Xiaobo
    Liu, Feng
    Liu, Tongliang
    Han, Bo
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [5] Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy
    Yu, Qing
    Aizawa, Kiyoharu
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 9517 - 9525
  • [6] Data Invariants to Understand Unsupervised Out-of-Distribution Detection
    Doorenbos, Lars
    Sznitman, Raphael
    Marquez-Neila, Pablo
    COMPUTER VISION, ECCV 2022, PT XXXI, 2022, 13691 : 133 - 150
  • [7] Unsupervised Continual Learning Using Cross-Level Discrimination and Evidential Pseudo Out-of-Distribution Detection Along With Gradient Projected Hard Attention
    Malviya, Ankit
    Maurya, Chandresh Kumar
    IEEE Access, 2024, 12 : 171143 - 171165
  • [8] Learning to Augment Distributions for Out-of-Distribution Detection
    Wang, Qizhou
    Fang, Zhen
    Zhang, Yonggang
    Liu, Feng
    Li, Yixuan
    Han, Bo
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [9] Out-of-distribution Detection with Boundary Aware Learning
    Pei, Sen
    Zhang, Xin
    Fan, Bin
    Meng, Gaofeng
    COMPUTER VISION, ECCV 2022, PT XXIV, 2022, 13684 : 235 - 251
  • [10] A MULTI-HEAD MODEL FOR CONTINUAL LEARNING VIA OUT-OF-DISTRIBUTION REPLAY
    Kim, Gyuhak
    Ke, Zixuan
    Liu, Bing
    CONFERENCE ON LIFELONG LEARNING AGENTS, VOL 199, 2022, 199