HieraASGSegNet: Hierarchical Context Fusion for Semantic Segmentation via Adaptive Superpixel Graph Reasoning
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Access"
DOI: 10.1109/access.2025.3626744
Abstract: Semantic segmentation remains challenging in real-world scenes due to variations in object scale, frequent occlusions, and ambiguous boundaries. We propose HieraASGSegNet, a hierarchical segmentation framework that performs adaptive superpixel graph reasoning. In this framework, each… read more here.
Keywords: graph reasoning; superpixel graph; segmentation; semantic segmentation ... See more keywords
Superpixel Graph Contrastive Clustering With Semantic-Invariant Augmentations for Hyperspectral Images
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Circuits and Systems for Video Technology"
DOI: 10.1109/tcsvt.2024.3418610
Abstract: Hyperspectral images (HSI) clustering is an important but challenging task. The state-of-the-art (SOTA) methods usually rely on superpixels, however, they do not fully utilize the spatial and spectral information in HSI 3-D structure, and their… read more here.
Keywords: superpixel graph; graph contrastive; semantic invariant; contrastive clustering ... See more keywords