Hidden Path Selection Network for Semantic Segmentation of Remote Sensing Images
This work addresses the challenge of depicting diverse land covers in remote sensing for applications like geographical analysis, but it is incremental as it builds on existing path selection methods with theoretical enhancements.
The paper tackles the problem of semantic segmentation in remote sensing images by addressing the limitation of homogeneous pixel-wise forward paths in deep models, proposing a Hidden Path Selection Network (HPS-Net) that improves performance on datasets like GID-5 and GID-15.
Targeting at depicting land covers with pixel-wise semantic categories, semantic segmentation in remote sensing images needs to portray diverse distributions over vast geographical locations, which is difficult to be achieved by the homogeneous pixel-wise forward paths in the architectures of existing deep models. Although several algorithms have been designed to select pixel-wise adaptive forward paths for natural image analysis, it still lacks theoretical supports on how to obtain optimal selections. In this paper, we provide mathematical analyses in terms of the parameter optimization, which guides us to design a method called Hidden Path Selection Network (HPS-Net). With the help of hidden variables derived from an extra mini-branch, HPS-Net is able to tackle the inherent problem about inaccessible global optimums by adjusting the direct relationships between feature maps and pixel-wise path selections in existing algorithms, which we call hidden path selection. For the better training and evaluation, we further refine and expand the 5-class Gaofen Image Dataset (GID-5) to a new one with 15 land-cover categories, i.e., GID-15. The experimental results on both GID-5 and GID-15 demonstrate that the proposed modules can stably improve the performance of different deep structures, which validates the proposed mathematical analyses.