DeepAI AI Chat
Log In Sign Up

SwiftNet: Real-time Video Object Segmentation

by   Haochen Wang, et al.

In this work we present SwiftNet for real-time semi-supervised video object segmentation (one-shot VOS), which reports 77.8 validation dataset, leading all present solutions in overall accuracy and speed performance. We achieve this by elaborately compressing spatiotemporal redundancy in matching-based VOS via Pixel-Adaptive Memory (PAM). Temporally, PAM adaptively triggers memory updates on frames where objects display noteworthy inter-frame variations. Spatially, PAM selectively performs memory update and match on dynamic pixels while ignoring the static ones, significantly reducing redundant computations wasted on segmentation-irrelevant pixels. To promote efficient reference encoding, light-aggregation encoder is also introduced in SwiftNet deploying reversed sub-pixel. We hope SwiftNet could set a strong and efficient baseline for real-time VOS and facilitate its application in mobile vision.


page 2

page 3

page 7


Region Aware Video Object Segmentation with Deep Motion Modeling

Current semi-supervised video object segmentation (VOS) methods usually ...

Fast Video Object Segmentation using the Global Context Module

We developed a real-time, high-quality video object segmentation algorit...

SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization

Matching-based methods, especially those based on space-time memory, are...

Pixel-Level Bijective Matching for Video Object Segmentation

Semi-supervised video object segmentation (VOS) aims to track the design...

Robust and Efficient Memory Network for Video Object Segmentation

This paper proposes a Robust and Efficient Memory Network, referred to a...

Causal graph-based video segmentation

Numerous approaches in image processing and computer vision are making u...

Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation

This paper presents a simple yet effective approach to modeling space-ti...