Scalable Video Object Segmentation with Simplified Framework

TL;DR

This paper introduces SimVOS, a scalable and simplified framework for video object segmentation that uses a single transformer backbone for joint feature extraction and matching, achieving state-of-the-art results.

Contribution

The paper proposes a unified transformer-based VOS framework that simplifies design and leverages pre-trained ViT models, improving performance and efficiency.

Findings

Achieves state-of-the-art results on DAVIS and YouTube-VOS benchmarks.

Effectively utilizes pre-trained ViT backbones like MAE for VOS.

Introduces token refinement for faster inference.

Abstract

The current popular methods for video object segmentation (VOS) implement feature matching through several hand-crafted modules that separately perform feature extraction and matching. However, the above hand-crafted designs empirically cause insufficient target interaction, thus limiting the dynamic target-aware feature learning in VOS. To tackle these limitations, this paper presents a scalable Simplified VOS (SimVOS) framework to perform joint feature extraction and matching by leveraging a single transformer backbone. Specifically, SimVOS employs a scalable ViT backbone for simultaneous feature extraction and matching between query and reference features. This design enables SimVOS to learn better target-ware features for accurate mask prediction. More importantly, SimVOS could directly apply well-pretrained ViT backbones (e.g., MAE) for VOS, which bridges the gap between VOS and large-scale self-supervised pre-training. To achieve a better performance-speed trade-off, we further explore within-frame attention and propose a new token refinement module to improve the running speed and save computational cost. Experimentally, our SimVOS achieves state-of-the-art results on popular video object segmentation benchmarks, i.e., DAVIS-2017 (88.0% J&F), DAVIS-2016 (92.9% J&F) and YouTube-VOS 2019 (84.2% J&F), without applying any synthetic video or BL30K pre-training used in previous VOS approaches.