Joint Inductive and Transductive Learning for Video Object Segmentation

被引:40
|
作者
Mao, Yunyao [1 ]
Wang, Ning [1 ]
Zhou, Wengang [1 ,2 ]
Li, Houqiang [1 ,2 ]
机构
[1] Univ Sci & Technol China, EEIS Dept, CAS Key Lab Technol GIPAS, Hefei, Anhui, Peoples R China
[2] Hefei Comprehens Natl Sci Ctr, Inst Artificial Intelligence, Hefei, Anhui, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
10.1109/ICCV48922.2021.00953
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Semi-supervised video object segmentation is a task of segmenting the target object in a video sequence given only a mask annotation in the first frame. The limited information available makes it an extremely challenging task. Most previous best-performing methods adopt matching-based transductive reasoning or online inductive learning. Nevertheless, they are either less discriminative for similar instances or insufficient in the utilization of spatio-temporal information. In this work, we propose to integrate transductive and inductive learning into a unified framework to exploit the complementarity between them for accurate and robust video object segmentation. The proposed approach consists of two functional branches. The transduction branch adopts a lightweight transformer architecture to aggregate rich spatio-temporal cues while the induction branch performs online inductive learning to obtain discriminative target information. To bridge these two diverse branches, a two-head label encoder is introduced to learn the suitable target prior for each of them. The generated mask encodings are further forced to be disentangled to better retain their complementarity. Extensive experiments on several prevalent benchmarks show that, without the need of synthetic training data, the proposed approach sets a series of new state-of-the-art records. Code is available at https://github.com/maoyunyao/JOINT.
引用
收藏
页码:9650 / 9659
页数:10
相关论文
共 50 条
  • [1] A Fast Video Object Segmentation Method Based on Inductive Learning and Transductive Reasoning
    Xu K.
    Li G.-R.
    Hong D.-X.
    Zhang W.-G.
    Qi Y.-K.
    Huang Q.-M.
    Jisuanji Xuebao/Chinese Journal of Computers, 2022, 45 (10): : 2117 - 2132
  • [2] A Transductive Approach for Video Object Segmentation
    Zhang, Yizhuo
    Wu, Zhirong
    Peng, Houwen
    Lin, Stephen
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 6947 - 6956
  • [3] SegFlow: Joint Learning for Video Object Segmentation and Optical Flow
    Cheng, Jingchun
    Tsai, Yi-Hsuan
    Wang, Shengjin
    Yang, Ming-Hsuan
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 686 - 695
  • [4] Temporal Transductive Inference for Few-Shot Video Object Segmentation
    Siam, Mennatullah
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2025,
  • [5] Video Segmentation with Joint Object and Trajectory Labeling
    Yang, Michael Ying
    Rosenhahn, Bodo
    2014 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2014, : 831 - 838
  • [6] Semi-Supervised Domain Adaptation via Joint Transductive and Inductive Subspace Learning
    Luo, Hao
    Tian, Zhiqiang
    Zhang, Kaibing
    Wang, Guofa
    Du, Shaoyi
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 10431 - 10445
  • [7] Joint Attention Mechanism for Unsupervised Video Object Segmentation
    Yao, Rui
    Xu, Xin
    Zhou, Yong
    Zhao, Jiaqi
    Fang, Liang
    PATTERN RECOGNITION AND COMPUTER VISION, PT I, 2021, 13019 : 154 - 165
  • [8] Learning Video Object Segmentation with Visual Memory
    Tokmakov, Pavel
    Inria, Karteek Alahari
    Schmid, Cordelia
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 4491 - 4500
  • [9] Adaptive Online Learning for Video Object Segmentation
    Wei, Li
    Xu, Chunyan
    Zhang, Tong
    INTELLIGENCE SCIENCE AND BIG DATA ENGINEERING: VISUAL DATA ENGINEERING, PT I, 2019, 11935 : 22 - 34
  • [10] Deep learning for video object segmentation: a review
    Gao, Mingqi
    Zheng, Feng
    Yu, James J. Q.
    Shan, Caifeng
    Ding, Guiguang
    Han, Jungong
    ARTIFICIAL INTELLIGENCE REVIEW, 2023, 56 (01) : 457 - 531