Results 11 to 20 of about 7,839,223 (287)

BM-NAS: Bilevel Multimodal Neural Architecture Search

Proceedings of the AAAI Conference on Artificial Intelligence, 2022
Deep neural networks (DNNs) have shown superior performances on various multimodal learning problems. However, it often requires huge efforts to adapt DNNs to individual multimodal tasks by manually engineering unimodal features and designing multimodal feature fusion strategies. This paper proposes Bilevel Multimodal Neural Architecture Search (BM-NAS)
Yihang Yin, Siyu Huang, Xiang Zhang 0001, Dejing Dou   +3 more
openaire   +4 more sources

PRE-NAS [PDF]

Proceedings of the Genetic and Evolutionary Computation Conference, 2022
Neural architecture search (NAS) aims to automate architecture engineering in neural networks. This often requires a high computational overhead to evaluate a number of candidate networks from the set of all possible networks in the search space during the search. Prediction of the networks' performance can alleviate this high computational overhead by
Yameng Peng, Andy Song, Vic Ciesielski, Haytham M. Fayek, Xiaojun Chang   +4 more
openaire   +5 more sources

M-NAS: Meta Neural Architecture Search

Proceedings of the AAAI Conference on Artificial Intelligence, 2020
Neural Architecture Search (NAS) has recently outperformed hand-crafted networks in various areas. However, most prevalent NAS methods only focus on a pre-defined task. For a previously unseen task, the architecture is either searched from scratch, which is inefficient, or transferred from the one obtained on some other task, which might be sub-optimal.
Jiaxing Wang, Jiaxiang Wu 0001, Haoli Bai, Jian Cheng 0001   +3 more
openaire   +3 more sources

NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization [PDF]

2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Recent advances on Out-of-Distribution (OoD) generalization reveal the robustness of deep learning models against distribution shifts. However, existing works focus on OoD algorithms, such as invariant risk minimization, domain generalization, or stable learning, without considering the influence of deep model architectures on OoD generalization, which
Haoyue Bai 0001, Fengwei Zhou, Lanqing Hong, Nanyang Ye 0001, S.-H. Gary Chan, Zhenguo Li   +5 more
openaire   +5 more sources

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   +2 more sources

DFG-NAS: Deep and Flexible Graph Neural Architecture Search [PDF]

CoRR, 2022
13 pages, 7 ...
Wentao Zhang 0001, Zheyu Lin, Yu Shen 0003, Yang Li 0106, Zhi Yang 0001, Bin Cui 0001   +5 more
openaire   +4 more sources

NAS-BNN: Neural Architecture Search for Binary Neural Networks

Pattern Recognition
23 ...
Zhihao Lin, Yongtao Wang, Jinhe Zhang, Xiaojie Chu, Haibin Ling   +4 more
openaire   +5 more sources

Neural Architecture Search Benchmarks: Insights and Survey [PDF]

IEEE Access, 2023
Neural Architecture Search (NAS), a promising and fast-moving research field, aims to automate the architectural design of Deep Neural Networks (DNNs) to achieve better performance on the given task and dataset.
Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath, Arun K. Somani   +3 more
doaj   +2 more sources

EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration

Proceedings of the AAAI Conference on Artificial Intelligence
Differentiable Architecture Search (DARTS) has achieved a rapid search for excellent architectures by optimizing architecture parameters through gradient descent. However, this efficiency comes with a significant challenge: the risk of premature convergence to local optima, resulting in subpar performance that falls short of expectations.
Zicheng Cai, Lei Chen, Peng Liu, Tongtao Ling, Yutao Lai   +4 more
openaire   +3 more sources

BN-NAS: Neural Architecture Search with Batch Normalization [PDF]

2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021
We present BN-NAS, neural architecture search with Batch Normalization (BN-NAS), to accelerate neural architecture search (NAS). BN-NAS can significantly reduce the time required by model training and evaluation in NAS. Specifically, for fast evaluation, we propose a BN-based indicator for predicting subnet performance at a very early training stage ...
Boyu Chen, Peixia Li, Baopu Li, Chen Lin 0003, Chuming Li, Ming Sun 0008, Junjie Yan, Wanli Ouyang   +7 more
openaire   +4 more sources