Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation

被引:0
|
作者
Wang, Ye [1 ]
Choi, Jongmoo [1 ]
Chen, Yueru [1 ]
Huang, Qin [1 ]
Li, Siyang [1 ]
Lee, Ming-Sui [2 ]
Kuo, C. -C. Jay [1 ]
机构
[1] Univ Southern Calif, Los Angeles, CA 91754 USA
[2] Natl Taiwan Univ, Taipei 10617, Taiwan
来源
关键词
Pseudo ground truth; Unsupervised; Video object segmentation;
D O I
10.1007/978-3-030-20870-7_32
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
One major technique debt in video object segmentation is to label the object masks for training instances. As a result, we propose to prepare inexpensive, yet high quality pseudo ground truth corrected with motion cue for video object segmentation training. Our method conducts semantic segmentation using instance segmentation networks and, then, selects the segmented object of interest as the pseudo ground truth based on the motion information. Afterwards, the pseudo ground truth is exploited to finetune the pretrained objectness network to facilitate object segmentation in the remaining frames of the video. We show that the pseudo ground truth could effectively improve the segmentation performance. This straightforward unsupervised video object segmentation method is more efficient than existing methods. Experimental results on DAVIS and FBMS show that the proposed method outperforms state-of-the-art unsupervised segmentation methods on various benchmark datasets. And the category-agnostic pseudo ground truth has great potential to extend to multiple arbitrary object tracking.
引用
收藏
页码:518 / 533
页数:16
相关论文
共 50 条
  • [1] A GROUND TRUTH FOR MOTION-BASED VIDEO-OBJECT SEGMENTATION
    Tiburzi, Fabrizio
    Escudero, Marcos
    Bescos, Jesus
    Martinez, Jose M.
    2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5, 2008, : 17 - 20
  • [2] Evaluating quality of motion for unsupervised video object segmentation
    Cheng, Guanjun
    Song, Huihui
    OPTOELECTRONICS LETTERS, 2024, 20 (06) : 379 - 384
  • [3] Evaluating quality of motion for unsupervised video object segmentation
    CHENG Guanjun
    SONG Huihui
    Optoelectronics Letters, 2024, 20 (06) : 379 - 384
  • [4] Learning Motion Guidance for Efficient Unsupervised Video Object Segmentation
    Zhao Z.-C.
    Zhang K.-H.
    Fan J.-Q.
    Liu Q.-S.
    Zidonghua Xuebao/Acta Automatica Sinica, 2023, 49 (04): : 872 - 880
  • [5] Unsupervised Online Video Object Segmentation With Motion Property Understanding
    Zhuo, Tao
    Cheng, Zhiyong
    Zhang, Peng
    Wong, Yongkang
    Kankanhalli, Mohan
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 : 237 - 249
  • [6] Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation
    Zhuge, Yunzhi
    Gu, Hongyu
    Zhang, Lu
    Qi, Jinqing
    Lu, Huchuan
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024,
  • [7] Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
    Cho, Suhwan
    Lee, Minhyeok
    Lee, Seunghoon
    Park, Chaewon
    Kim, Donghyeong
    Lee, Sangyoun
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 5129 - 5138
  • [8] Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering
    Xi, Lin
    Chen, Weihai
    Wu, Xingming
    Liu, Zhong
    Li, Zhengguo
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (02) : 995 - 1006
  • [9] Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation
    Xi, Lin
    Chen, Weihai
    Wu, Xingming
    Liu, Zhong
    Li, Zhengguo
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (09) : 6279 - 6292
  • [10] Unsupervised Video Object Segmentation with Motion-Based Bilateral Networks
    Li, Siyang
    Seybold, Bryan
    Vorobyov, Alexey
    Lei, Xuejing
    Kuo, C-C Jay
    COMPUTER VISION - ECCV 2018, PT III, 2018, 11207 : 215 - 231