Weakly-supervised Semantic Segmentation in Cityscape via Hyperspectral Image
This work addresses the high cost of manual labeling for semantic segmentation in complex urban scenes, offering a more efficient solution for practitioners and researchers in computer vision and remote sensing.
This paper explores weakly-supervised semantic segmentation in urban environments using hyperspectral images (HSIs). The authors propose a framework that leverages the rich spectral information in HSIs to refine coarse labels, achieving competitive segmentation results and even superior edge fineness compared to manually annotated labels for certain classes.
High-resolution hyperspectral images (HSIs) contain the response of each pixel in different spectral bands, which can be used to effectively distinguish various objects in complex scenes. While HSI cameras have become low cost, algorithms based on it have not been well exploited. In this paper, we focus on a novel topic, weakly-supervised semantic segmentation in cityscape via HSIs. It is based on the idea that high-resolution HSIs in city scenes contain rich spectral information, which can be easily associated to semantics without manual labeling. Therefore, it enables low cost, highly reliable semantic segmentation in complex scenes. Specifically, in this paper, we theoretically analyze the HSIs and introduce a weakly-supervised HSI semantic segmentation framework, which utilizes spectral information to improve the coarse labels to a finer degree. The experimental results show that our method can obtain highly competitive labels and even have higher edge fineness than artificial fine labels in some classes. At the same time, the results also show that the refined labels can effectively improve the effect of semantic segmentation. The combination of HSIs and semantic segmentation proves that HSIs have great potential in high-level visual tasks.