Results 251 to 260 of about 738,909 (270)

MIGO-NAS: Towards Fast and Generalizable Neural Architecture Search

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
Neural architecture search (NAS) has achieved unprecedented performance in various computer vision tasks. However, most existing NAS methods are defected in search efficiency and model generalizability. In this paper, we propose a novel NAS framework, termed MIGO-NAS, with the aim to guarantee the efficiency and generalizability in arbitrary search ...
Xiawu Zheng, Rongrong Ji, Yuhang Chen, Qiang Wang, Baochang Zhang, Jie Chen, Qixiang Ye, Feiyue Huang, Yonghong Tian   +8 more
openaire   +2 more sources

FTT-NAS: Discovering Fault-Tolerant Neural Architecture

2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC), 2020
With the fast evolvement of deep-learning specific embedded computing systems, applications powered by deep learning are moving from the cloud to the edge. When deploying NNs onto the edge devices under complex environments, there are various types of possible faults: soft errors caused by atmospheric neutrons and radioactive impurities, voltage ...
Wenshuo Li, Xuefei Ning, Guangjun Ge, Xiaoming Chen, Yu Wang, Huazhong Yang   +5 more
openaire   +1 more source

Features Of Komsomolsk-Na-Amure Architectural Image

European Proceedings of Social and Behavioural Sciences, 2021
Purpose to identify features of Komsomolsk-na-Amure architectural image and the influence of the urban image on human perception. Methodology is based on a comprehensive analysis of the city imagery. The author reveals the features of the formation of urban space. The definition of the concept of the architectural image of the city is given.
openaire   +1 more source

GP-NAS: Gaussian Process Based Neural Architecture Search

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Neural architecture search (NAS) advances beyond the state-of-the-art in various computer vision tasks by automating the designs of deep neural networks. In this paper, we aim to address three important questions in NAS: (1) How to measure the correlation between architectures and their performances?
Zhihang Li, Teng Xi, Jiankang Deng, Gang Zhang, Shengzhao Wen, Ran He   +5 more
openaire   +1 more source

RoCo-NAS: Robust and Compact Neural Architecture Search

2021 International Joint Conference on Neural Networks (IJCNN), 2021
Deep model compression has been studied widely, and state-of-the-art methods can now achieve high compression ratios with minimum accuracy loss. Recent advances in adversarial attacks reveal the inherent vulnerability of deep neural networks to slightly perturbed images called adversarial examples.
Vahid Geraeinejad, Sima Sinaei, Mehdi Modarressi, Masoud Daneshtalab   +3 more
openaire   +1 more source

NAS-PED: Neural Architecture Search for Pedestrian Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Pedestrian detection currently suffers from two issues in crowded scenes: occlusion and dense boundary prediction, making it still challenging in complex real-world scenarios. In recent years, Convolutional Neural Networks (CNN) and Vision Transformers (ViT) have shown their superiorities in addressing these issues, where ViTs capture global feature ...
Yi Tang, Min Liu, Baopu Li, Yaonan Wang, Wanli Ouyang   +4 more
openaire   +2 more sources

FTR-NAS: Fault-Tolerant Recurrent Neural Architecture Search

2020
With the popularity of the applications equipped with neural networks on edge devices, robustness has become the focus of researchers. However, when deploying the applications onto the hardware, environmental noise is unavoidable, in which errors may cause applications crash, especially for the safety-critic applications.
Kai Hu, Dong Ding, Shuo Tian, Rui Gong, Li Luo, Lei Wang   +5 more
openaire   +1 more source

CaW-NAS: Compression Aware Neural Architecture Search

2022 25th Euromicro Conference on Digital System Design (DSD), 2022
Hadjer Benmeziane, Hamza Ouranoughi, Smail Niar, Kaoutar El Maghraoui   +3 more
openaire   +1 more source

Quantum-Enhanced Neural Architecture Search (Q-NAS)

Neural Architecture Search (NAS) is critical in automating neural network design, but it's hindered by high computational costs and complex search spaces. Quantum-enhanced Neural Architecture Search (Q-NAS) proposes a solution by integrating quantum computing principles to tackle these challenges. Leveraging quantum mechanics, Q-NAS utilizes algorithms
openaire   +1 more source

DLW-NAS: Differentiable Light-Weight Neural Architecture Search

Cognitive Computation, 2022
Shu Li, Yuxu Mao, Fuchang Zhang, Dong Wang, Guoqiang Zhong   +4 more
openaire   +1 more source