Feedback Neural Network for Weakly Supervised Geo-Semantic Segmentation
This addresses the problem of expensive labeling in geo-semantic segmentation for mapping applications, but it appears incremental as it builds on existing weakly-supervised methods.
The paper tackles weakly-supervised semantic segmentation for satellite imagery by proposing a neural network that suppresses irrelevant neuron activations, achieving superior performance and efficiency compared to baseline models.
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.