SWT: Self-Supervised Video Object Segmentation via Sliding, Wavelet and Transportation
This paper proposes self-supervised VOS with Sliding window, Wavelet transform and optimal Transport (SWT), a self-supervised VOS framework entirely trained on static dataset using contrastive learning that achieves excellent results on five VOS datasets as well as an additional body part propagation dataset.
Zheng Zhu, Jia-Qing Fan, Han-Wen Qian et al.
· ACM Transactions on Multimed... · 0 citations