Memorizing Features Efficiently for Self-supervised Video Object Segmentation

Read full text Summarise with VIRAT
Authors: Marcelo Mendonça, Luciano Rebouças de Oliveira
Cited by: 0
References: 28

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

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.

Fields of Study & Subjects

Advanced Neural Network Applications Video Surveillance and Tracking Methods Domain Adaptation and Few-Shot Learning

Publication details

Journal / source
Journal of the Brazilian Computer Society
Volume
32
Issue
1
Pages
443–452
Publication date
15 March 2026
Language
EN