Bottom-up top-down cues for weakly-supervised semantic segmentation
We consider the task of learning a classifier for semantic segmentation using weak supervision in the form of image labels specifying objects present in the image. Our method uses deep convolutional neural networks (cnns) and adopts an Expectation-Maximization (EM) based approach. We focus on the fo...
Auteurs principaux: | Hou, Q, Massiceti, D, Dokania, P, Wei, Y, Cheng, M, Torr, P |
---|---|
Format: | Conference item |
Publié: |
Springer, Cham
2018
|
Documents similaires
-
OBJCUT: efficient segmentation using top-down and bottom-up cues.
par: Kumar, M, et autres
Publié: (2010) -
OBJCUT: efficient segmentation using top-down and bottom-up cues
par: Kumar, MP, et autres
Publié: (2009) -
Discovering class-specific pixels for weakly-supervised semantic segmentation
par: Chaudhry, A, et autres
Publié: (2017) -
Exploring bottom-up and top-down cues with attentive learning for webly supervised object detection
par: Wu, Zhonghua, et autres
Publié: (2020) -
Bottom-up or top-down?
par: Johansen-Berg, H
Publié: (2001)