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

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

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

6 Sitaatiot (Scopus)

Abstrakti

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.
AlkuperäiskieliEnglanti
OtsikkoComputer Vision ACCV 2016
Alaotsikko13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part I
ToimittajatShang-Hong Lai, Vincent Lepetit, Ko Nishino, Yoichi Sato
Sivut163-179
DOI - pysyväislinkit
TilaJulkaistu - 2017
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaAsian Conference on Computer Vision - Taipei, Taiwan
Kesto: 20 marraskuuta 201624 marraskuuta 2016
Konferenssinumero: 13

Julkaisusarja

NimiLecture Notes in Computer Science
KustantajaSpringer
Vuosikerta10111
ISSN (painettu)0302-9743

Conference

ConferenceAsian Conference on Computer Vision
LyhennettäACCV
MaaTaiwan
KaupunkiTaipei
Ajanjakso20/11/201624/11/2016

Sormenjälki Sukella tutkimusaiheisiin 'Semi-Supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

  • Siteeraa tätä

    Wang, H., Raiko, T., Lensu, L., Wang, T., & Karhunen, J. (2017). Semi-Supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation. teoksessa S-H. Lai, V. Lepetit, K. Nishino, & Y. Sato (Toimittajat), Computer Vision ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part I (Sivut 163-179). (Lecture Notes in Computer Science; Vuosikerta 10111). https://doi.org/10.1007/978-3-319-54181-5_11