Metraipolis › archive › dc_40481863db95
SWT: Self-Supervised Video Object Segmentation via Sliding, Wavelet and Transportation — arXiv:2609.31725
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31725
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:59:27.824Z
- SHA-256 of the archived text
afc7cb466487ec2c5b94673029bacd8c7c75650aba56a0656e455d1a83937775- Stable URL of this page
https://metraipolis.com/documento/dc_40481863db95
How to cite
SWT: Self-Supervised Video Object Segmentation via Sliding, Wavelet and Transportation — arXiv:2609.31725 — arXiv (en), https://arxiv.org/abs/2609.31725 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_40481863db95 (Metraipolis archive dc_40481863db95, sha256 afc7cb466487ec2c5b94673029bacd8c7c75650aba56a0656e455d1a83937775)
BibTeX
@misc{dc40481863db95,
title = {SWT: Self-Supervised Video Object Segmentation via Sliding, Wavelet and Transportation — arXiv:2609.31725},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31725},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_40481863db95; sha256 afc7cb466487ec2c5b94673029bacd8c7c75650aba56a0656e455d1a83937775},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31725. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Video Object Segmentation (VOS) aims to accurately segment target objects from consecutive video frames and track the changes of the objects in each frame of the video. Conventional VOS methods typically demand substantial quantities of pixel-level labeled video sequences for fully supervised learning, which limits the performance of the model in sparse video scenes, while existing VOS methods have limited adaptability to global changes in objects. Based on this observation, in this paper, we propose 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. Firstly, a rolling sample buffer reuses overlapping groups of independently sampled images across successive updates. Secondly, to address the long-distance modeling difficulty caused by simple convolutional structures, we introduce wavelet transform to expand the receptive field of convolutional kernels, thus improving the model's representational capability. Finally, we incorporate optimal transport to assist the model in finding the globally optimal match between the target across two frames, improving the model's ability to handle nonrigid deformations of objects. SWT only requires training on the COCO dataset once and achieves excellent results on five VOS datasets as well as an additional body part propagation dataset. The code will be released soon at [ this https URL ]( this https URL ). Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.31725 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:02.122Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).