To address this, we adopt a superpixel representation and develop a robust iterative learning strategy that combines noise-aware training of segmentation network and noisy label refinement, both guided by the superpixels. This design enables us to exploit the structural constraints in segmentation labels...
wsi-superpixel-guided-labeling是一种基于超像素引导的标注方法,主要用于医学图像分析。通过将医学图像分割成多个超像素区域,然后利用这些超像素区域作为标注单元,实现对图像中不同结构和组织的准确标注。这种方法能够有效减少标注工作的复杂度,提高标注的精度和效率。同时,wsi-superpixel-guided-labeling还可以结合深度学习...
学术范收录的Journal Superpixel guided structure sparsity for multispectral and hyperspectral image fusion over couple dictionary,目前已有全文资源,进入学术范阅读全文,查看参考文献与引证文献,参与文献内容讨论。学术范是一个在线学术交流社区,收录论文、作者
Weakly-supervised semantic segmentation with superpixel guided local and global consistency作者: Highlights: • An introduction of superpixel knowledge into affinity based segmentation approach. • An iterative framework that achieve an effective collaboration of the superpixel information. and the features...
To handle the irregular spatial dependency of remote sensing images and mitigate the conflict between limited labeled samples and training demand, we design a superpixel-guided layer-wise embedding CNN (SLE-CNN) for remote sensing image classification, which can efficiently exploit the information from...
In this paper, we propose a novel superpixel-guided two-view geometric model fitting method (called SDF), which can obtain reliable and consistent results for real images. Specifically, SDF includes three main parts: a deterministic sampling algorithm, a model hypothesis updating strategy and a ...
Superpixel-guided CFAR detection of ships at sea in SAR imagerydoi:10.1109/ICASSP.2017.7952436Odysseas A. PappasAlin M. AchimDavid R. BullIEEEInternational Conference on Acoustics, Speech, and Signal Processing
We propose a method called superpixel-guided manifold sparse NMF (SMSNMF) for HU. Unlike traditional NMF-based approaches, SMSNMF effectively utilizes spatial information within a regularized manifold, establishing a robust connection between the original image and its associated abundance maps. Further...
Image super-resolutionWe propose a novel superpixel-guided nonlocal means (SNLM) method.The performance of SNLM is better than the existing NLM method.SNLM adaptively selects thekneighbors in a flexible search region and does not require an empirical study on the search window size.SNLM is ...
Secondly, we design a pixel-based CNN and a two-scale superpixel-based GCN classification framework for weighted feature fusion. Compared with several excellent band selection methods, the superb performance of our feature extraction module is verified. In addition, under the condition of only five...