A video saliency detector trained with 20% manual labels plus flow-generated pseudo-labels outperforms fully supervised state-of-the-art methods on VOS, DAVIS, and FBMS.
Deep contrast learning for salient object detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Semi-Supervised Video Salient Object Detection Using Pseudo-Labels
A video saliency detector trained with 20% manual labels plus flow-generated pseudo-labels outperforms fully supervised state-of-the-art methods on VOS, DAVIS, and FBMS.