Feedback Neural Network for Weakly Supervised Geo-Semantic Segmentation

Estimated read time 1 min read

Feedback Neural Network for Weakly Supervised Geo-Semantic Segmentation

Learning from weakly-supervised data is one of the main challenges in machine learning and computer vision, especially for tasks such as image semantic segmentation where labeling is extremely expensive and subjective. In this paper, we propose a novel neural network architecture to perform weakly-supervised learning by suppressing irrelevant neuron activations. It localizes objects of interest by learning from image-level categorical labels in an end-to-end manner. We apply this algorithm to a practical challenge of transforming satellite images into a map of settlements and individual buildings. Experimental results show that the proposed algorithm achieves superior performance and efficiency when compared with various baseline models.

Comments: 9 pages, 4 figures
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:1612.02766 [cs.CV]
(or arXiv:1612.02766v1 [cs.CV] for this version)

https://arxiv.org/abs/1612.02766

You May Also Like

More From Author

+ There are no comments

Add yours