Space-time memory (STM) network methods have been dominant in semi-supervised video object segmentation (SVOS) due to their remarkable performance. In this work, we identify three key aspects where we can improve such methods; i) supervisory signal, ii) pretraining and iii) spatial awareness. We then propose TrickVOS; a generic, method-agnostic bag of tricks addressing each aspect with i) a structure-aware hybrid loss, ii) a simple decoder pretraining regime and iii) a cheap tracker that imposes spatial constraints in model predictions. Finally, we propose a lightweight network and show that when trained with TrickVOS, it achieves competitive results to state-of-the-art methods on DAVIS and YouTube benchmarks, while being one of the first STM-based SVOS methods that can run in real-time on a mobile device.
@article{arxiv.2306.15377,
title = {TrickVOS: A Bag of Tricks for Video Object Segmentation},
author = {Evangelos Skartados and Konstantinos Georgiadis and Mehmet Kerim Yucel and Koskinas Ioannis and Armando Domi and Anastasios Drosou and Bruno Manganelli and Albert Saa-Garriga},
journal= {arXiv preprint arXiv:2306.15377},
year = {2023}
}