Results 71 to 80 of about 7,252 (198)

Dissecting Glioma Heterogeneity: A Deep Hybrid Graph Convolutional Network With Hinge Attention for Causal‐Effect Explainability

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Brain tumour classification is a critical task in medical imaging that requires accurate and interpretable solutions to assist in clinical decision‐making. In this paper, we present GraphConvNet‐X, a novel hybrid model that integrates convolutional neural networks (CNNs) for spatial feature extraction with graph neural networks (GNNs) that ...
Sultanul Arifeen Hamim, Mubasshar U. I. Tamim, S. M. Hasan Mahmud, M. F. Mridha, Zeyar Aung   +4 more
wiley   +1 more source

Visualizing Image Segmentation Network Behavior Through the Lens of Scale Space Analysis

Computer Graphics Forum, EarlyView.
Abstract Deep neural networks are widely used for image segmentation, also in sensitive applications such as medical imaging or autonomous driving. However, few explainable AI methods are available that help developers understand such networks beyond classification.
A. C. Mikliss, T. Schultz
wiley   +1 more source

Residual swin transformer for classifying the types of cotton pests in complex background

Frontiers in Plant Science
BackgroundCotton pests have a major impact on cotton quality and yield during cotton production and cultivation. With the rapid development of agricultural intelligence, the accurate classification of cotton pests is a key factor in realizing the precise
Ting Zhang, Jikui Zhu, Fengkui Zhang, Shijie Zhao, Wei Liu, Ruohong He, Hongqiang Dong, Qingqing Hong, Changwei Tan, Ping Li   +9 more
doaj   +1 more source

Comparing deep learning models for butterfly and moth (Lepidoptera) species identification

Insect Conservation and Diversity, EarlyView.
Deep learning models open new possibilities for the processing of image‐based species records. We used high‐performance computing to compare 40 models for butterfly and moth species identification based on a citizen science dataset with over 500,000 images of 162 species.
Friederike Barkmann, Andreas Lindner, Johannes Rüdisser   +2 more
wiley   +1 more source

Deep Learning Models for Detection of Periapical Radiolucent Lesions on Panoramic Radiographs: A Systematic Review and Meta‐Analysis

International Endodontic Journal, EarlyView.
ABSTRACT Background Panoramic radiographs are used routinely to screen dental conditions and treatment patterns. Recently, numerous studies have suggested that deep learning (DL) models can be utilized for analysing panoramic radiographs. Objective This review aimed to evaluate the accuracy of DL models in detecting periapical radiolucent lesions (PRLs)
Ibrahim Ali Ahmad, Raidan Ba‐Hattab, Sadeq Ali Al‐Maweri, Faleh Tamimi   +3 more
wiley   +1 more source

Application of Noise2Inverse and adaptation (Noise2Phase) to single‐mask x‐ray phase contrast micro‐computed tomography

Journal of Microscopy, EarlyView.
Abstract X‐ray phase contrast imaging (XPCI), when implemented in micro‐computed tomography (micro‐CT) mode, offers high‐contrast 3D imaging of weakly‐attenuating material samples. In the so‐called single‐mask edge illumination approach, a mask with periodically spaced transmitting apertures is used to split the x‐ray beam into narrow beamlets; when ...
Khushal Shah, Grammatiki Lioliou, Dai Chen, Alexander Denker, Peter Munro, Marco Endrizzi, Alberto Astolfo, Alessandro Olivo, Charlotte K. Hagen   +8 more
wiley   +1 more source

FML-Swin: An Improved Swin Transformer Segmentor for Remote Sensing Images

IEEE Access
Semantic segmentation of urban remote sensing images is a very challenging task. Due to the complex background, occlusion overlap and small scale target of urban remote sensing image, the semantic segmentation results have some defects such as target confusion and similarity, target boundary ambiguity, and small scale target omission.
Tianren Wu, Wenqin Deng, Rui Lin, Junzhe Jiang 0004, Xueyun Chen   +4 more
openaire   +2 more sources

Frequency Domain and Gradient-Spatial Multi-Scale Swin KANsformer for Remote Sensing Scene Classification

Remote Sensing
Transformer-based deep learning techniques have recently shown outstanding potential in remote sensing scene classification (RSSC), benefiting from their ability to capture global semantic relationships and contextual dependencies.
Xiaozhang Zhu, Junqing Huang, Haihui Wang   +2 more
doaj   +1 more source

Human‐in‐the‐loop eider duck counting in Arctic Canada with an open‐vocabulary multispecies wildlife detector

AI Magazine, Volume 47, Issue 3, Fall 2026.
Abstract Accurate monitoring of eider duck populations in Arctic Canada is essential for understanding ecosystem health and supporting conservation efforts in a rapidly changing climate. Traditional manual counting from aerial imagery is time‐consuming, labor‐intensive, and prone to observer bias.
Jayden Hsiao, Aryan Kalia, Zhonghao Zhang, Hudson Sun, Muhammed Patel, David A. Clausi, Lincoln Linlin Xu, Becky Segal, Joel Heath   +8 more
wiley   +1 more source

Multi-scale capsule Swin Transformer-based method for SAR image target recognition

Tongxin xuebao
A multi-scale capsule Swin Transformer network (MSCSTN) was proposed by synergizing the semantic feature encoding of capsule units with the context feature mapping of Swin Transformer. Capsule encoding and the Swin Transformer were jointly applied to SAR
HOU Yuchao, WANG Jie, LI Hongtao, HAO Yan, DUAN Xiaoqi, HUANG Kaiwen, TIAN Youliang   +6 more
doaj