SHLS: Superfeatures learned from still images for self-supervised VOS
Marcelo M Santos (UFBA),* Jefferson Fontinele da Silva (University Federal of Maranhão), Luciano Oliveira (UFBA)
The 34th British Machine Vision Conference
Abstract
Self-supervised video object segmentation (VOS) aims at eliminating the need for manual annotations to learn VOS. However, existing methods often require extensive training data consisting of hours of videos. In this paper, we introduce a novel approach that combines superpixels and deep learning features through metric learning, enabling us to learn VOS from a small dataset of unlabeled still images. Our method, called superfeatures in a highly compressed latent space (SHLS), embeds convolutional features into the corresponding superpixel areas, resulting in ultra-compact image representations. This allowed us to construct an efficient memory mechanism to store and retrieve past information throughout a frame sequence to support current frame segmentation. We evaluate our method on the popular DAVIS dataset and achieve competitive results compared to state-of-the-art self-supervised methods, which were trained with much larger video-based datasets. We have made our code and trained model publicly available at: https://github.com/IvisionLab/SHLS.Video
Citation
@inproceedings{Santos_2023_BMVC,
author = {Marcelo M Santos and Jefferson Fontinele da Silva and Luciano Oliveira},
title = {SHLS: Superfeatures learned from still images for self-supervised VOS},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0523.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by