Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleSeptember 2024
ICDaIR: Distribution-aware Static IR Drop Prediction Flow Based on Image Classification
MLCAD '24: Proceedings of the 2024 ACM/IEEE International Symposium on Machine Learning for CADArticle No.: 4, Pages 1–6https://doi.org/10.1145/3670474.3685942During the integrated circuit design process, the maximum IR drop value is often given more attention. The frequency of the maximum IR drop in the actual circuits presents an uneven dispersion, i.e., long-tail distribution. To address this problem, this ...
- research-articleSeptember 2024
Removing cloud shadows from ground-based solar imagery
Machine Vision and Applications (MVAA), Volume 35, Issue 6https://doi.org/10.1007/s00138-024-01607-2AbstractThe study and prediction of space weather entails the analysis of solar images showing structures of the Sun’s atmosphere. When imaged from the Earth’s ground, images may be polluted by terrestrial clouds which hinder the detection of solar ...
- research-articleSeptember 2024
Deep RegNet-150 architecture for single image super resolution of real-time unpaired image data
AbstractSingle Image Super-Resolution (SISR) is a fundamental computer vision task aimed at enhancing the spatial resolution and quality of low-resolution images. In recent years, deep learning techniques have revolutionized the field of SISR, enabling ...
Graphical AbstractDisplay Omitted
Highlights- A U-shaped deep net with 150 layers called Deep RegNet-150 is presented for the SISR.
- The 150 layers of the deep regression network are modelled with a Residual Channel Attention Block (RCAB).
- The down sampling portion of U-Net has ...
- ArticleAugust 2024
BioU-Net: Diagnosis Network Based on Spectral Feature Enhancement for Myocardial Infarction
Advanced Intelligent Computing Technology and ApplicationsPages 340–351https://doi.org/10.1007/978-981-97-5663-6_29AbstractMyocardial infarction (MI) is a dangerous cardiovascular disease. Electrocardiogram (ECG), as a non-invasive testing tool, plays an important role in the diagnosis of cardiovascular diseases. In recent years, deep learning technology has provided ...
-
- ArticleAugust 2024
TMU: Transmission-Enhanced Mamba-UNet for Medical Image Segmentation
Advanced Intelligent Computing Technology and ApplicationsPages 428–438https://doi.org/10.1007/978-981-97-5609-4_33AbstractIn the field of medical image segmentation, the Mamba-UNet is seen as a diamond in the rough due to its robust capability in capturing long-range interactions within images while maintaining linear computational complexity. However, the existing ...
- ArticleAugust 2024
Color Image Steganography Based on Two-Channel Preprocessing and U-Net Network
Advanced Intelligent Computing Technology and ApplicationsPages 56–68https://doi.org/10.1007/978-981-97-5603-2_5AbstractThe advancement of technology provides convenience for information transmission, but there are still security issues in the information transmission process where secret information may be stolen. With the increasing application of the U-Net ...
- research-articleSeptember 2024
Partial class activation mapping guided graph convolution cascaded U-Net for retinal vessel segmentation
Computers in Biology and Medicine (CBIM), Volume 178, Issue Chttps://doi.org/10.1016/j.compbiomed.2024.108736AbstractAccurate segmentation of retinal vessels in fundus images is of great importance for the diagnosis of numerous ocular diseases. However, due to the complex characteristics of fundus images, such as various lesions, image noise and complex ...
Highlights- A network that can enforce feature consistency is constructed.
- Graph structure is used to model the structural redundancy information of retinal vessels.
- Partial class activation mapping is introduced as consequent network to ...
- research-articleJuly 2024
SRU-Net: a novel spatiotemporal attention network for sclera segmentation and recognition
Pattern Analysis & Applications (PAAS), Volume 27, Issue 3https://doi.org/10.1007/s10044-024-01301-zAbstractSegmenting sclera images for effective recognition under non-cooperative conditions poses a significant challenge due to the prevalent noise. While U-Net-based methods have shown success, their limitations in accurately segmenting objects with ...
- ArticleJuly 2024
Image Reconstruction for Proton Therapy Range Verification via U-NETs
- Lena M. Setterdahl,
- William R. B. Lionheart,
- Sean Holman,
- Kyrre Skjerdal,
- Hunter N. Ratliff,
- Kristian Smeland Ytre-Hauge,
- Danny Lathouwers,
- Ilker Meric
AbstractThis study aims to investigate the capability of U-Nets in improving image reconstruction accuracy for proton range verification within the framework of the NOVO (Next generation imaging for real-time dose verification enabling adaptive proton ...
- research-articleJuly 2024
MSU-Net: the multi-scale supervised U-Net for image splicing forgery localization
Pattern Analysis & Applications (PAAS), Volume 27, Issue 3https://doi.org/10.1007/s10044-024-01305-9AbstractImage splicing forgery, that is, copying some parts of an image into another image, is one of the frequently used tampering methods in image forgery. As a research hotspot in recent years, deep learning has been used in image forgery detection. ...
- research-articleJuly 2024
MAF-Net: A multi-attention fusion network for power transmission line extraction from aerial images
Expert Systems with Applications: An International Journal (EXWA), Volume 250, Issue Chttps://doi.org/10.1016/j.eswa.2024.123936AbstractAutomatic extraction of power transmission lines from remote sensing images is important for intelligent power inspection. However, this task faces many challenges, such as complex backgrounds and varying illumination, which make accurate ...
Highlights- A multi-attention fusion network is proposed for accurate power line extraction.
- A multi-scale context fusion block is proposed for effective feature learning.
- A hybrid feature pooling block is to address the information loss ...
- ArticleJuly 2024
MRI Brain Cancer Image Detection: Application of an Integrated U-Net and ResNet50 Architecture
AbstractBrain cancer results in the deaths of many people each year. Magnetic Resonance Imaging (MRI) is used to segment different regions of brain tumors, such as edema and tumor cores, which is challenging due to differences in location, size, shape, ...
- ArticleJuly 2024
Segmentation of Cytology Images to Detect Cervical Cancer Using Deep Learning Techniques
AbstractCervical cancer is the fourth most common cancer among women. Every year, more than 200,000 women die due to cervical cancer; however, it is a preventable disease if detected early. This study aims to detect cervical cancer by identifying the ...
- research-articleJuly 2024
Toward deep drum source separation
Pattern Recognition Letters (PTRL), Volume 183, Issue CPages 86–91https://doi.org/10.1016/j.patrec.2024.04.026AbstractIn the past, the field of drum source separation faced significant challenges due to limited data availability, hindering the adoption of cutting-edge deep learning methods that have found success in other related audio applications. In this ...
Highlights- The present work is the first to leverage deep learning for drum source separation.
- We introduce the largest dataset of isolated drum stems to date (1224 hours).
- We introduce the first real-time deep drum source separation model.
- research-articleJuly 2024
SaraNet: Semantic aggregation reverse attention network for pulmonary nodule segmentation
Computers in Biology and Medicine (CBIM), Volume 177, Issue Chttps://doi.org/10.1016/j.compbiomed.2024.108674AbstractAccurate segmentation of pulmonary nodule is essential for subsequent pathological analysis and diagnosis. However, current U-Net architectures often rely on a simple skip connection scheme, leading to the fusion of feature maps with different ...
Highlights- The Semantic Aggregation Pyramid (SAP) module, based on channel-wise cross-attention mechanism and feature pyramid, is proposed to replaces the skip connections in U-Net. This module mitigates the detrimental effects of simple skip ...
- research-articleAugust 2024
Image deblurring based on local features and long-range dependencies
ARAEML '24: Proceedings of the 2024 International Conference on Advanced Robotics, Automation Engineering and Machine LearningPages 89–97https://doi.org/10.1145/3677454.3677469Dynamic scene deblurring is a complex problem that involves blurring caused by camera shake and object movement. While deep learning methods have made significant progress in many the field of image deblurring, there is still room for improvement. This ...
- research-articleAugust 2024
UCTransNeXt: Global and local information fusion for retinal vessel segmentation
ARAEML '24: Proceedings of the 2024 International Conference on Advanced Robotics, Automation Engineering and Machine LearningPages 68–74https://doi.org/10.1145/3677454.3677466The precise segmentation of retinal blood vessels is essential for the early diagnosis of various ophthalmic diseases. Meanwhile, the U-shaped structure based on convolutional neural networks performs well in medical image segmentation. However, due to ...
- research-articleJune 2024
PSC diffusion: patch-based simplified conditional diffusion model for low-light image enhancement
AbstractLow-light image enhancement is pivotal for augmenting the utility and recognition of visuals captured under inadequate lighting conditions. Previous methods based on Generative Adversarial Networks (GAN) are affected by mode collapse and lack ...
- research-articleJune 2024
CST-UNet: Cross Swin Transformer Enhanced U-Net with Masked Bottleneck for Single-Channel Speech Enhancement
Circuits, Systems, and Signal Processing (CSSP), Volume 43, Issue 9Pages 5989–6010https://doi.org/10.1007/s00034-024-02736-9AbstractSpeech enhancement performance has improved significantly with the introduction of deep learning models, especially methods based on the Long–Short-Term Memory architecture. However, these methods face challenges such as high computational ...