Semi-Supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation

Huiling Wang, Tapani Raiko, Lasse Lensu, Tinghuai Wang, Juha Karhunen

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

10 Citations (Scopus)

Abstract

Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labelled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively exploiting the representation power of CNN with limited training data remains a challenge. Simply borrowing the existing pre-trained CNN image recognition model for video segmentation task can severely hurt performance. We propose a semi-supervised approach to adapting CNN image recognition model trained from labelled image data to the target domain exploiting both semantic evidence learned from CNN, and the intrinsic structures of video data. By explicitly modelling and compensating for the domain shift from the source domain to the target domain, this proposed approach underpins a robust semantic object segmentation method against the changes in appearance, shape and occlusion in natural videos. We present extensive experiments on challenging datasets that demonstrate the superior performance of our approach compared with the state-of-the-art methods.
Original languageEnglish
Title of host publicationComputer Vision ACCV 2016
Subtitle of host publication13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part I
EditorsShang-Hong Lai, Vincent Lepetit, Ko Nishino, Yoichi Sato
Pages163-179
DOIs
Publication statusPublished - 2017
MoE publication typeA4 Article in a conference publication
EventAsian Conference on Computer Vision - Taipei, Taiwan, Republic of China
Duration: 20 Nov 201624 Nov 2016
Conference number: 13

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume10111
ISSN (Print)0302-9743

Conference

ConferenceAsian Conference on Computer Vision
Abbreviated titleACCV
Country/TerritoryTaiwan, Republic of China
CityTaipei
Period20/11/201624/11/2016

Fingerprint

Dive into the research topics of 'Semi-Supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation'. Together they form a unique fingerprint.

Cite this