Results 151 to 160 of about 9,095 (206)

Vine Spread for Superpixel Segmentation

IEEE Transactions on Image Processing, 2023
Superpixel is the over-segmentation region of an image, whose basic units “pixels” have similar properties. Although many popular seeds-based algorithms have been proposed to improve the segmentation quality of superpixels, they still suffer from the ...
Pei Zhou, Xuejing Kang, Anlong Ming
semanticscholar   +3 more sources

Hyperspectral Image Classification With Multi-Attention Transformer and Adaptive Superpixel Segmentation-Based Active Learning

IEEE Transactions on Image Processing, 2023
Deep learning (DL) based methods represented by convolutional neural networks (CNNs) are widely used in hyperspectral image classification (HSIC). Some of these methods have strong ability to extract local information, but the extraction of long-range ...
Chunhui Zhao, Boao Qin, Shou Feng, Wenxiang Zhu, Weiwei SUN, Wei Li, X. Jia   +6 more
semanticscholar   +1 more source

What Catch Your Attention in SAR Images: Saliency Detection Based on Soft-Superpixel Lacunarity Cue

IEEE Transactions on Geoscience and Remote Sensing, 2023
In existing superpixel-wise saliency detection algorithms, superpixel generation often is an isolated preprocessing step. The performance of saliency maps is determined by the accuracy of superpixels to a certain extent.
Fei Ma, Xuejiao Sun, Fan Zhang, Yongsheng Zhou, Hengchao Li   +4 more
semanticscholar   +1 more source

Lightweight Image Super-Resolution with Superpixel Token Interaction

IEEE International Conference on Computer Vision, 2023
Transformer-based methods have demonstrated impressive results on single-image super-resolution (SISR) task. However, self-attention mechanism is computationally expensive when applied to the entire image.
Aiping Zhang, Wenqi Ren, Yi Liu, Xiaochun Cao   +3 more
semanticscholar   +1 more source

Hyperspectral Image Classification Using a Superpixel–Pixel–Subpixel Multilevel Network

IEEE Transactions on Instrumentation and Measurement, 2023
Hyperspectral images (HSIs) often contain irregular ground cover with mixed spectral features and noise, which makes it challenging to identify the ground cover using only pixel features, superpixel features, or a combination of both.
Bing Tu, Qi Ren, Qianming Li, Wangquan He, W. He   +4 more
semanticscholar   +1 more source

CNN-Enhanced Graph Convolutional Network With Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification

IEEE Transactions on Geoscience and Remote Sensing, 2020
Recently, the graph convolutional network (GCN) has drawn increasing attention in the hyperspectral image (HSI) classification. Compared with the convolutional neural network (CNN) with fixed square kernels, GCN can explicitly utilize the correlation ...
Qichao Liu, Liang Xiao, Jingxiang Yang, Zhihui Wei   +3 more
semanticscholar   +1 more source

autoSMIM: Automatic Superpixel-Based Masked Image Modeling for Skin Lesion Segmentation

IEEE Transactions on Medical Imaging, 2023
Skin lesion segmentation from dermoscopic images plays a vital role in early diagnoses and prognoses of various skin diseases. However, it is a challenging task due to the large variability of skin lesions and their blurry boundaries.
Zhonghua Wang, Junyan Lyu, Xiaoying Tang
semanticscholar   +1 more source

CNN-Improved Superpixel-to-Pixel Fuzzy Graph Convolution Network for PolSAR Image Classification

IEEE Transactions on Geoscience and Remote Sensing, 2023
Superpixel-based graph convolutional network (S-GCN) has shown the advantages of less computational time and global modeling ability for polarimetric synthetic aperture radar (PolSAR) image classification.
Junfei Shi, Tiansheng He, Shanshan Ji, Mengmeng Nie, Haiyan Jin   +4 more
semanticscholar   +1 more source

Constrained Superpixel Tracking

IEEE Transactions on Cybernetics, 2018
In this paper, we propose a constrained graph labeling algorithm for visual tracking where nodes denote superpixels and edges encode the underlying spatial, temporal, and appearance fitness constraints. First, the spatial smoothness constraint, based on a transductive learning method, is enforced to leverage the latent manifold structure in feature ...
Lijun Wang, Huchuan Lu, Ming-Hsuan Yang
openaire   +2 more sources

Adaptive Superpixel for Active Learning in Semantic Segmentation

IEEE International Conference on Computer Vision, 2023
Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive. To reduce the annotation cost, we propose a superpixel-based active learning (AL) framework, which collects a dominant label per superpixel instead.
Hoyoung Kim, Minhyeon Oh, S. Hwang, Suha Kwak, Jungseul Ok   +4 more
semanticscholar   +1 more source