Dynamic Video Segmentation Network

2018-04-03 · CVPR 2018 6 · Yu-Syuan Xu, Tsu-Jui Fu, Hsuan-Kung Yang, Chun-Yi Lee

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% mIoU at 19.8 fps on the Cityscape dataset. A high speed version of DVSNet is able to deliver an fps of 30.4 with 63.2% mIoU on the same dataset. DVSNet is also able to reduce up to 95% of the computational workloads.

📄 PDF Abstract BibTeX arXiv:1804.00931

Code (0)

등록된 구현이 없습니다.

Tasks

Segmentation Video Segmentation Video Semantic Segmentation

Dynamic Face Video Segmentation via Reinforcement Learning

2019-07-02 · CVPR 2020 6 · Yujiang Wang, Mingzhi Dong, Jie Shen, Yang Wu 외

For real-time semantic video segmentation, most recent works utilised a dynamic framework with a key scheduler to make online key/non-key decisions. Some works used a fixed key scheduling policy, while others proposed ad…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+4

Value of Temporal Dynamics Information in Driving Scene Segmentation

2019-03-21 · Li Ding, Jack Terwilliger, Rini Sherony, Bryan Reimer 외

Semantic scene segmentation has primarily been addressed by forming representations of single images both with supervised and unsupervised methods. The problem of semantic segmentation in dynamic scenes has begun to rece…

Scene Segmentation Segmentation Semantic Segmentation Video Object Segmentation+1

Learning Unsupervised Video Object Segmentation Through Visual Attention

2019-06-01 · CVPR 2019 6 · Wenguan Wang, Hongmei Song, Shuyang Zhao, Jianbing Shen 외

This paper conducts a systematic study on the role of visual attention in Unsupervised Video Object Segmentation (UVOS) tasks. By elaborately annotating three popular video segmentation datasets (DAVIS, Youtube-Objects a…

Object Segmentation Semantic Segmentation Unsupervised Video Object Segmentation+3

Unsupervised Learning Consensus Model for Dynamic Texture Videos Segmentation

2020-06-29 · Lazhar Khelifi, Max Mignotte

Dynamic texture (DT) segmentation, and video processing in general, is currently widely dominated by methods based on deep neural networks that require the deployment of a large number of layers. Although this parametric…

parameter estimation Segmentation

SDI-Paste: Synthetic Dynamic Instance Copy-Paste for Video Instance Segmentation

2024-10-16 · Sahir Shrestha, Weihao Li, Gao Zhu, Nick Barnes

Data augmentation methods such as Copy-Paste have been studied as effective ways to expand training datasets while incurring minimal costs. While such methods have been extensively implemented for image level tasks, we f…

Data Augmentation Instance Segmentation MORPH Semantic Segmentation+1