PD-DARTS: Progressive Discretization Differentiable Architecture Search

Li, Yonggang; Zhou, Yafeng; Wang, Yongtao; Tang, Zhi

doi:10.1007/978-3-030-59830-3_26

Cited by 757 publications

(2,685 citation statements)

References 2 publications

Supporting

Mentioning

2,669

Contrasting

Unclassified

Order By: Relevance

“…NAS vs. D/T-NAS. Traditional NAS (e.g., DARTS [25]) randomly sample half data from the training set as support set while the remaining half as query set. In contrast, D/T-NAS ( Fig.…”

Section: Domain/type-aware Meta-nasmentioning

confidence: 99%

NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing

Wan

Qin

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

133

View full text Add to dashboard Cite

Face anti-spoofing (FAS) plays a vital role in securing face recognition systems. Existing methods heavily rely on the expert-designed networks, which may lead to a sub-optimal solution for FAS task. Here we propose the first FAS method based on neural architecture search (NAS), called NAS-FAS, to discover the well-suited task-aware networks. Unlike previous NAS works mainly focus on developing efficient search strategies in generic object classification, we pay more attention to study the search spaces for FAS task. The challenges of utilizing NAS for FAS are in two folds: the networks searched on 1) a specific acquisition condition might perform poorly in unseen conditions, and 2) particular spoofing attacks might generalize badly for unseen attacks. To overcome these two issues, we develop a novel search space consisting of central difference convolution and pooling operators. Moreover, an efficient static-dynamic representation is exploited for fully mining the FAS-aware spatio-temporal discrepancy. Besides, we propose Domain/Type-aware Meta-NAS, which leverages cross-domain/type knowledge for robust searching. Finally, in order to evaluate the NAS transferability for cross datasets and unknown attack types, we release a large-scale 3D mask dataset, namely CASIA-SURF 3DMask, for supporting the new 'cross-dataset cross-type' testing protocol. Experiments demonstrate that the proposed NAS-FAS achieves state-of-the-art performance on nine FAS benchmark datasets with four testing protocols.

show abstract

“…NAS vs. D/T-NAS. Traditional NAS (e.g., DARTS [25]) randomly sample half data from the training set as support set while the remaining half as query set. In contrast, D/T-NAS ( Fig.…”

Section: Domain/type-aware Meta-nasmentioning

confidence: 99%

NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing

Wan

Qin

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

133

View full text Add to dashboard Cite

show abstract

“…Lorraine et al [108] introduce an algorithm for inexpensive GD-based hyperparameter optimization. Liu et al [109] employ GD in the DARTS algorithm, which optimizes both the network weights and the architecture. The authors use relaxation tricks to make a weighted sum of candidate operations differentiable, and then apply the gradient descent method to directly train the weights.…”

Section: Nas Based On Gdmentioning

confidence: 99%

“…The authors use relaxation tricks to make a weighted sum of candidate operations differentiable, and then apply the gradient descent method to directly train the weights. Inspired by DARTS [109], Dong et al [110] introduce gradientbased search using the differentiable architecture sampler (GDAS) method. The authors develop a differentiable architecture sampler which samples individual architectures in a differentiable way to accelerate the architecture search procedure.…”

Section: Nas Based On Gdmentioning

confidence: 99%

From federated learning to federated neural architecture search: a survey

Zhu

Zhang

Jin

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Federated learning is a recently proposed distributed machine learning paradigm for privacy preservation, which has found a wide range of applications where data privacy is of primary concern. Meanwhile, neural architecture search has become very popular in deep learning for automatically tuning the architecture and hyperparameters of deep neural networks. While both federated learning and neural architecture search are faced with many open challenges, searching for optimized neural architectures in the federated learning framework is particularly demanding. This survey paper starts with a brief introduction to federated learning, including both horizontal, vertical, and hybrid federated learning. Then neural architecture search approaches based on reinforcement learning, evolutionary algorithms and gradient-based are presented. This is followed by a description of federated neural architecture search that has recently been proposed, which is categorized into online and offline implementations, and single- and multi-objective search approaches. Finally, remaining open research questions are outlined and promising research topics are suggested.

show abstract

“…Impressive results have been shown for reinforcement learning (RL) for example [31], [32]. Recent methods like differentiable architecture search (DARTs) [33] reduce the search time by formulating the task in a differentiable manner. To reduce the redundancy in the network space, partiallyconnected DARTs (PC-DARTs) was recently introduced to perform a more efficient search without compromising the performance of DARTS [34].…”

Section: F Neural Architecture Searchmentioning

confidence: 99%

A Review of Recent Advances of Binary Neural Networks for Edge Computing

Zhao

Gong

et al. 2021

IEEE J. Miniat. Air Space Syst.

View full text Add to dashboard Cite

Edge computing is promising to become one of the next hottest topics in artificial intelligence because it benefits various evolving domains such as real-time unmanned aerial systems, industrial applications, and the demand for privacy protection. This paper reviews recent advances on binary neural network (BNN) and 1-bit CNN technologies that are well suitable for front-end, edge-based computing. We introduce and summarize existing work and classify them based on gradient approximation, quantization, architecture, loss functions, optimization method, and binary neural architecture search. We also introduce applications in the areas of computer vision and speech recognition and discuss future applications for edge computing.

show abstract

PD-DARTS: Progressive Discretization Differentiable Architecture Search

Cited by 757 publications

References 2 publications

NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing

NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing

From federated learning to federated neural architecture search: a survey

A Review of Recent Advances of Binary Neural Networks for Edge Computing

Contact Info

Product

Resources

About