OGNet proposes an output-guided attention module from multi-scale outputs and an intractable area F-measure loss to enhance salient object detection in edges and confusing areas while remaining lightweight.
Learning to detect salient objects with image-level supervision,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
OGNet: Salient Object Detection with Output-guided Attention Module
OGNet proposes an output-guided attention module from multi-scale outputs and an intractable area F-measure loss to enhance salient object detection in edges and confusing areas while remaining lightweight.