Online Adaptation of Convolutional Neural Networks for Video Object Segmentation

06/28/2017
by   Paul Voigtlaender, et al.
0

We tackle the task of semi-supervised video object segmentation, i.e. segmenting the pixels belonging to an object in the video using the ground truth pixel mask for the first frame. We build on the recently introduced one-shot video object segmentation (OSVOS) approach which uses a pretrained network and fine-tunes it on the first frame. While achieving impressive performance, at test time OSVOS uses the fine-tuned network in unchanged form and is not able to adapt to large changes in object appearance. To overcome this limitation, we propose Online Adaptive Video Object Segmentation (OnAVOS) which updates the network online using training examples selected based on the confidence of the network and the spatial configuration. Additionally, we add a pretraining step based on objectness, which is learned on PASCAL. Our experiments show that both extensions are highly effective and improve the state of the art on DAVIS to an intersection-over-union score of 85.7

READ FULL TEXT

page 2

page 4

research
11/16/2016

One-Shot Video Object Segmentation

This paper tackles the task of semi-supervised video object segmentation...
research
12/03/2020

Make One-Shot Video Object Segmentation Efficient Again

Video object segmentation (VOS) describes the task of segmenting a set o...
research
09/27/2019

Adaptive ROI Generation for Video Object Segmentation Using Reinforcement Learning

In this paper, we aim to tackle the task of semi-supervised video object...
research
04/03/2018

Dynamic Video Segmentation Network

In this paper, we present a detailed design of dynamic video segmentatio...
research
03/28/2019

Fast video object segmentation with Spatio-Temporal GANs

Learning descriptive spatio-temporal object models from data is paramoun...
research
05/17/2022

Collaborative Attention Memory Network for Video Object Segmentation

Semi-supervised video object segmentation is a fundamental yet Challengi...
research
04/10/2023

Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation

Video Panoptic Segmentation (VPS) aims to achieve comprehensive pixel-le...

Please sign up or login with your details

Forgot password? Click here to reset