Weight-sharing neural architecture search: A battle to shrink the optimization gap
Neural architecture search (NAS) has attracted increasing attention. In recent years,
individual search methods have been replaced by weight-sharing search methods for higher …
individual search methods have been replaced by weight-sharing search methods for higher …
Searching efficient 3d architectures with sparse point-voxel convolution
Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive
safely. Given the limited hardware resources, existing 3D perception models are not able to …
safely. Given the limited hardware resources, existing 3D perception models are not able to …
EMONAS-Net: Efficient multiobjective neural architecture search using surrogate-assisted evolutionary algorithm for 3D medical image segmentation
MB Calisto, SK Lai-Yuen - Artificial intelligence in medicine, 2021 - Elsevier
Deep learning plays a critical role in medical image segmentation. Nevertheless, manually
designing a neural network for a specific segmentation problem is a very difficult and time …
designing a neural network for a specific segmentation problem is a very difficult and time …
MI-UNet: multi-inputs UNet incorporating brain parcellation for stroke lesion segmentation from T1-weighted magnetic resonance images
Stroke is a serious manifestation of various cerebrovascular diseases and one of the most
dangerous diseases in the world today. Volume quantification and location detection of …
dangerous diseases in the world today. Volume quantification and location detection of …
Pvnas: 3d neural architecture search with point-voxel convolution
3D neural networks are widely used in real-world applications (eg, AR/VR headsets, self-
driving cars). They are required to be fast and accurate; however, limited hardware …
driving cars). They are required to be fast and accurate; however, limited hardware …
A review of AutoML optimization techniques for medical image applications
Automatic analysis of medical images using machine learning techniques has gained
significant importance over the years. A large number of approaches have been proposed …
significant importance over the years. A large number of approaches have been proposed …
Lidarnas: Unifying and searching neural architectures for 3d point clouds
Developing neural models that accurately understand objects in 3D point clouds is essential
for the success of robotics and autonomous driving. However, arguably due to the higher …
for the success of robotics and autonomous driving. However, arguably due to the higher …
Ldmres-Net: a lightweight neural network for efficient medical image segmentation on iot and edge devices
In this study, we propose LDMRes-Net, a lightweight dual-multiscale residual block-based
convolutional neural network tailored for medical image segmentation on IoT and edge …
convolutional neural network tailored for medical image segmentation on IoT and edge …
[PDF][PDF] 基于U-Net 结构改进的医学影像分割技术综述
殷晓航， 王永才， 李德英 - 软件学报, 2020 - jos.org.cn
深度学习在医学影像分割领域得到广泛应用, 其中, 2015 年提出的U-Net 因其分割小目标效果较
好, 结构具有可扩展性, 自提出以来受到广泛关注. 近年来, 随着医学图像割性能要求的提升 …
好, 结构具有可扩展性, 自提出以来受到广泛关注. 近年来, 随着医学图像割性能要求的提升 …
Density-aware U-net for unstructured environment dust segmentation
Y Fu, M Gao, G Xie, M Hu, C Wei… - IEEE Sensors Journal, 2024 - ieeexplore.ieee.org
Vision-based segmentation methods rely heavily on image quality, and mining
environments are full of dust, which greatly reduces visibility. Efficient and accurate …
environments are full of dust, which greatly reduces visibility. Efficient and accurate …