Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation

@inproceedings{Hou2017BottomUpTC,
  title={Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation},
  author={Qibin Hou and Daniela Massiceti and P. Dokania and Yunchao Wei and Ming-Ming Cheng and Philip H. S. Torr},
  booktitle={EMMCVPR},
  year={2017}
}
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 following three aspects of EM: (i) initialization; (ii) latent posterior estimation (E-step) and (iii) the parameter update (M-step). We show that saliency and attention maps, bottom-up and top-down… Expand
Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation.
Harvesting Information from Captions for Weakly Supervised Semantic Segmentation
Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation
Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation
Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation
...
1
2
3
4
...

References

SHOWING 1-10 OF 42 REFERENCES
STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation
Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation
Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
From image-level to pixel-level labeling with Convolutional Networks
Constrained Convolutional Neural Networks for Weakly Supervised Segmentation
Fully Convolutional Multi-Class Multiple Instance Learning
Deeply Supervised Salient Object Detection with Short Connections
...
1
2
3
4
5
...