liu.seSearch for publications in DiVA
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Discriminative Learning and Target Attention for the 2019 DAVIS Challenge onVideo Object Segmentation
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten. ETH Zürich.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.ORCID-id: 0000-0002-6096-3648
2019 (engelsk)Inngår i: CVPR 2019 workshops: DAVIS Challenge on Video Object Segmentation, 2019Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

In this work, we address the problem of semi-supervised video object segmentation, where the task is to segment a target object in every image of the video sequence, given a ground truth only in the first frame. To be successful it is crucial to robustly handle unpredictable target appearance changes and distracting objects in the background. In this work we obtain a robust and efficient representation of the target by integrating a fast and light-weight discriminative target model into a deep segmentation network. Trained during inference, the target model learns to discriminate between the local appearances of target and background image regions. Its predictions are enhanced to accurate segmentation masks in a subsequent refinement stage.To further improve the segmentation performance, we add a new module trained to generate global target attention vectors, given the input mask and image feature maps. The attention vectors add semantic information about thetarget from a previous frame to the refinement stage, complementing the predictions provided by the target appearance model. Our method is fast and requires no network fine-tuning. We achieve a combined J and F-score of 70.6 on the DAVIS 2019 test-challenge data

sted, utgiver, år, opplag, sider
2019.
Emneord [en]
video object segmentation, computer vision, machine learning
HSV kategori
Identifikatorer
URN: urn:nbn:se:liu:diva-163334OAI: oai:DiVA.org:liu-163334DiVA, id: diva2:1390580
Konferanse
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Tilgjengelig fra: 2020-02-01 Laget: 2020-02-01 Sist oppdatert: 2020-02-01

Open Access i DiVA

Fulltekst mangler i DiVA

Personposter BETA

Robinson, AndreasJäremo-Lawin, FelixDanelljan, MartinFelsberg, Michael

Søk i DiVA

Av forfatter/redaktør
Robinson, AndreasJäremo-Lawin, FelixDanelljan, MartinFelsberg, Michael
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric

urn-nbn
Totalt: 50 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf