DeepAI AI Chat
Log In Sign Up

Dynamic Video Segmentation Network

by   Yu-Syuan Xu, et al.
National Tsing Hua University

In this paper, we present a detailed design of dynamic video segmentation network (DVSNet) for fast and efficient semantic video segmentation. DVSNet consists of two convolutional neural networks: a segmentation network and a flow network. The former generates highly accurate semantic segmentations, but is deeper and slower. The latter is much faster than the former, but its output requires further processing to generate less accurate semantic segmentations. We explore the use of a decision network to adaptively assign different frame regions to different networks based on a metric called expected confidence score. Frame regions with a higher expected confidence score traverse the flow network. Frame regions with a lower expected confidence score have to pass through the segmentation network. We have extensively performed experiments on various configurations of DVSNet, and investigated a number of variants for the proposed decision network. The experimental results show that our DVSNet is able to achieve up to 70.4 speed version of DVSNet is able to deliver an fps of 30.4 with 63.2 the same dataset. DVSNet is also able to reduce up to 95% of the computational workloads.


page 1

page 2

page 4


Efficient Video Semantic Segmentation with Labels Propagation and Refinement

This paper tackles the problem of real-time semantic segmentation of hig...

Online Adaptation of Convolutional Neural Networks for Video Object Segmentation

We tackle the task of semi-supervised video object segmentation, i.e. se...

Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video

In this paper, we present Accel, a novel semantic video segmentation sys...

Dynamic Face Video Segmentation via Reinforcement Learning

For real-time semantic video segmentation, most recent works utilise a d...

Fast Interactive Video Object Segmentation with Graph Neural Networks

Pixelwise annotation of image sequences can be very tedious for humans. ...

Separable Convolutional LSTMs for Faster Video Segmentation

Semantic Segmentation is an important module for autonomous robots such ...

Fast Full-frame Video Stabilization with Iterative Optimization

Video stabilization refers to the problem of transforming a shaky video ...

Code Repositories


Modified implementation for DVSNet based on Tensorflow

view repo