READMem: Robust Embedding Association for a Diverse Memory in Unconstrained Video Object Segmentation
Stephane Vujasinovic (Fraunhofer IOSB),* Sebastian W Bullinger (Fraunhofer IOSB), Stefan Becker (Fraunhofer IOSB), Norbert Scherer-Negenborn (Fraunhofer IOSB), Michael Arens (Fraunhofer IOSB), Rainer Stiefelhagen (Karlsruhe Institute of Technology)
The 34th British Machine Vision Conference
Abstract
We present READMem (Robust Embedding Association for a Diverse Memory), a modular framework for semi-automatic video object segmentation (sVOS) methods designed to handle unconstrained videos. Contemporary sVOS works typically aggregate video frames in an ever-expanding memory, demanding high hardware resources for long-term applications. To mitigate memory requirements and prevent near object duplicates (caused by information of adjacent frames), previous methods introduce a hyper-parameter that controls the frequency of frames eligible to be stored. This parameter has to be adjusted according to concrete video properties (such as rapidity of appearance changes and video length) and does not generalize well. Instead, we integrate the embedding of a new frame into the memory only if it increases the diversity of the memory content. Furthermore, we propose a robust association of the embeddings stored in the memory with query embeddings during the update process. Our approach avoids the accumulation of redundant data, allowing us in return, to restrict the memory size and prevent extreme memory demands in long videos. We extend popular sVOS baselines with READMem, which previously showed limited performance on long videos. Our approach achieves competitive results on the Long-time Video dataset (LV1) while not hindering performance on short sequences. Our code is publicly available at https://github.com/Vujas-Eteph/READMem.Video
Citation
@inproceedings{Vujasinovic_2023_BMVC,
author = {Stephane Vujasinovic and Sebastian W Bullinger and Stefan Becker and Norbert Scherer-Negenborn and Michael Arens and Rainer Stiefelhagen},
title = {READMem: Robust Embedding Association for a Diverse Memory in Unconstrained Video Object Segmentation},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0603.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by