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...
Váldodahkkit: | Hou, Q, Massiceti, D, Dokania, P, Wei, Y, Cheng, M, Torr, P |
---|---|
Materiálatiipa: | Conference item |
Almmustuhtton: |
Springer, Cham
2018
|
Geahča maid
-
OBJCUT: efficient segmentation using top-down and bottom-up cues.
Dahkki: Kumar, M, et al.
Almmustuhtton: (2010) -
OBJCUT: efficient segmentation using top-down and bottom-up cues
Dahkki: Kumar, MP, et al.
Almmustuhtton: (2009) -
Discovering class-specific pixels for weakly-supervised semantic segmentation
Dahkki: Chaudhry, A, et al.
Almmustuhtton: (2017) -
Exploring bottom-up and top-down cues with attentive learning for webly supervised object detection
Dahkki: Wu, Zhonghua, et al.
Almmustuhtton: (2020) -
Bottom-up or top-down?
Dahkki: Johansen-Berg, H
Almmustuhtton: (2001)