EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Memorizing Features Efficiently for Self-supervised Video Object Segmentation

Marcelo Mendonça, Luciano Oliveira

Journal of the Brazilian Computer Society · 15.03.2026 · 32 (1) · 443-452

DOI: 10.5753/jbcs.2026.5904 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Brazilian Computer Society, online erschienen am 15.03.2026. Verfasst von Marcelo Mendonça und 1 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Video object segmentation (VOS) involves consistently identifying and classifying object pixels in video sequences, a task that traditionally depends on extensive, manually annotated datasets. In this work, we present SHLS (Superfeatures in a Highly Compressed Latent Space), a self-supervised VOS method that reduces reliance on both annotations and large training datasets. SHLS employs a metric learning framework combining superpixels and deep learning features, enabling effective training with just 10,000 unlabeled still images. Utilizing an efficient memory clustering mechanism, SHLS generates ultra-compact representations called superfeatures, which efficiently store and classify object information across video sequences. Experiments on the DAVIS dataset demonstrate SHLS's strong performance in multi-object scenarios, underscoring its potential as a robust and efficient alternative in self-supervised VOS.

Zitieren

APA

Mendonça, M., & Oliveira, L. (2026). Memorizing Features Efficiently for Self-supervised Video Object Segmentation. Journal of the Brazilian Computer Society, 32(1), 443-452. https://doi.org/10.5753/jbcs.2026.5904

Vancouver

Mendonça M, Oliveira L. Memorizing Features Efficiently for Self-supervised Video Object Segmentation. Journal of the Brazilian Computer Society. 2026;32(1):443-452. doi:10.5753/jbcs.2026.5904

BibTeX
@article{Mendona2026,
  author = {Mendonça, Marcelo and Oliveira, Luciano},
  title = {Memorizing Features Efficiently for Self-supervised Video Object Segmentation},
  journal = {Journal of the Brazilian Computer Society},
  year = {2026},
  volume = {32},
  number = {1},
  pages = {443--452},
  doi = {10.5753/jbcs.2026.5904}
}
Kostenlos starten →