Directional Deep Embedding and Appearance Learning for Fast Video Object Segmentation

02/17/2020
by   Yingjie Yin, et al.
9

Most recent semi-supervised video object segmentation (VOS) methods rely on fine-tuning deep convolutional neural networks online using the given mask of the first frame or predicted masks of subsequent frames. However, the online fine-tuning process is usually time-consuming, limiting the practical use of such methods. We propose a directional deep embedding and appearance learning (DDEAL) method, which is free of the online fine-tuning process, for fast VOS. First, a global directional matching module, which can be efficiently implemented by parallel convolutional operations, is proposed to learn a semantic pixel-wise embedding as an internal guidance. Second, an effective directional appearance model based statistics is proposed to represent the target and background on a spherical embedding space for VOS. Equipped with the global directional matching module and the directional appearance model learning module, DDEAL learns static cues from the labeled first frame and dynamically updates cues of the subsequent frames for object segmentation. Our method exhibits state-of-the-art VOS performance without using online fine-tuning. Specifically, it achieves a J F mean score of 74.8 2017 dataset and an overall score G of 71.3 dataset, while retaining a speed of 25 fps with a single NVIDIA TITAN Xp GPU. Furthermore, our faster version runs 31 fps with only a little accuracy loss. Our code and trained networks are available at https://github.com/YingjieYin/Directional-Deep-Embedding-and-Appearance-Learning-for-Fast-Video-Object-Segmentation.

READ FULL TEXT

page 8

page 12

page 13

page 14

page 15

page 16

page 17

page 18

research
02/25/2019

FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation

Many of the recent successful methods for video object segmentation (VOS...
research
08/19/2019

In defense of OSVOS

As a milestone for video object segmentation, one-shot video object segm...
research
04/18/2019

Discriminative Online Learning for Fast Video Object Segmentation

We address the highly challenging problem of video object segmentation. ...
research
09/04/2018

VideoMatch: Matching based Video Object Segmentation

Video object segmentation is challenging yet important in a wide variety...
research
09/27/2019

DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation

In this paper, we propose the differentiable mask-matching network (DMM-...
research
08/28/2019

Fast Video Object Segmentation via Mask Transfer Network

Accuracy and processing speed are two important factors that affect the ...
research
04/15/2020

A Transductive Approach for Video Object Segmentation

Semi-supervised video object segmentation aims to separate a target obje...

Please sign up or login with your details

Forgot password? Click here to reset