IIIT Hyderabad Publications |
|||||||||
|
Self-Supervised Feature Learning for Semantic Segmentation of Overhead ImageryAuthors: Suriya Singh,Anil Batra,Guan Pang,Lorenzo Torresani,Saikat Basu,Manohar Paluri,C V Jawahar Conference: British Machine Vision Conference (BMVC 2018) Location United Kingdom Date: 2018-09-03 Report no: IIIT/TR/2018/148 AbstractOverhead imageries play a crucial role in many applications such as urban planning, crop yield forecasting, mapping, and policy making. Semantic segmentation could en-able automatic, efficient, and large-scale understanding of overhead imageries for these applications. However, semantic segmentation of overhead imageries is a hallenging task, primarily due to the large domain gap from existing research in ground imageries, unavailability of large-scale dataset with pixel-level annotations, and inherent complex-ity in the task. Readily available vast amount of unlabeled overhead imageries share more common structures and patterns compared to the ground imageries, therefore, its large-scale analysis could benefit from unsupervised feature learning techniques. In this work, we study various self-supervised feature learning techniques for se-mantic segmentation of overhead imageries. We choose image semantic inpainting as a self-supervised task [36] for our experiments due to its proximity to the semantic seg-mentation task. We (i) show that existing approaches are inefficient for semantic segmen-tation, (ii) propose architectural changes towards self-supervised learning for semantic segmentation, (iii) propose an adversarial training scheme for self-supervised learning by increasing the pretext task’s difficulty gradually and show that it leads to learning better features, and (iv) propose a unified approach for overhead scene parsing, road network extraction, and land cover estimation. Our approach improves over training from scratch by more than 10% and ImageNet pre-trained network by more than 5% m IOU . Full paper: pdf Centre for Visual Information Technology |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |