TY - GEN
T1 - A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation
AU - Ponimatkin, Georgy
AU - Samet, Nermin
AU - Xiao, Yang
AU - Du, Yuming
AU - Marlet, Renaud
AU - Lepetit, Vincent
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023/1/1
Y1 - 2023/1/1
N2 - We propose a simple, yet powerful approach for unsupervised object segmentation in videos. We introduce an objective function whose minimum represents the mask of the main salient object over the input sequence. It only relies on independent image features and optical flows, which can be obtained using off-the-shelf self-supervised methods. It scales with the length of the sequence with no need for superpixels or sparsification, and it generalizes to different datasets without any specific training. This objective function can actually be derived from a form of spectral clustering applied to the entire video. Our method achieves on-par performance with the state of the art on standard bench-marks (DAVIS2016, SegTrack-v2, FBMS59), while being conceptually and practically much simpler.
AB - We propose a simple, yet powerful approach for unsupervised object segmentation in videos. We introduce an objective function whose minimum represents the mask of the main salient object over the input sequence. It only relies on independent image features and optical flows, which can be obtained using off-the-shelf self-supervised methods. It scales with the length of the sequence with no need for superpixels or sparsification, and it generalizes to different datasets without any specific training. This objective function can actually be derived from a form of spectral clustering applied to the entire video. Our method achieves on-par performance with the state of the art on standard bench-marks (DAVIS2016, SegTrack-v2, FBMS59), while being conceptually and practically much simpler.
KW - Algorithms: Video recognition and understanding (tracking, action recognition, etc.)
KW - Machine learning architectures
KW - and algorithms (including transfer, low-shot, semi-, self-, and un-supervised learning)
KW - formulations
UR - https://www.scopus.com/pages/publications/85149028129
U2 - 10.1109/WACV56688.2023.00584
DO - 10.1109/WACV56688.2023.00584
M3 - Conference contribution
AN - SCOPUS:85149028129
T3 - Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
SP - 5881
EP - 5892
BT - Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023
Y2 - 3 January 2023 through 7 January 2023
ER -