Weight-sharing neural architecture search: A battle to shrink the optimization gap

L ** out of performance collapse without indicators
X Chu, X Wang, B Zhang, S Lu, X Wei, J Yan - arxiv preprint arxiv …, 2020 - arxiv.org
Despite the fast development of differentiable architecture search (DARTS), it suffers from
long-standing performance instability, which extremely limits its application. Existing …

Progressive darts: Bridging the optimization gap for nas in the wild

X Chen, L **e, J Wu, Q Tian - International Journal of Computer Vision, 2021 - Springer
With the rapid development of neural architecture search (NAS), researchers found powerful
network architectures for a wide range of vision tasks. Like the manually designed …

Direct differentiable augmentation search

A Liu, Z Huang, Z Huang… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Data augmentation has been an indispensable tool to improve the performance of deep
neural networks, however the augmentation can hardly transfer among different tasks and …

Fine-tuning darts for image classification

MS Tanveer, MUK Khan… - 2020 25th International …, 2021 - ieeexplore.ieee.org
Neural Architecture Search (NAS) has gained attraction due to superior classification
performance. Differential Architecture Search (DARTS) is a computationally light method. To …

Zarts: On zero-order optimization for neural architecture search

X Wang, W Guo, J Su, X Yang… - Advances in Neural …, 2022 - proceedings.neurips.cc
Differentiable architecture search (DARTS) has been a popular one-shot paradigm for NAS
due to its high efficiency. It introduces trainable architecture parameters to represent the …

ALADA: A lite automatic data augmentation framework for industrial defect detection

Y Wang, SH Chung, WA Khan, T Wang… - Advanced Engineering …, 2023 - Elsevier
Industrial defect detection is a critical and challenging task in the quality control of
manufacturing production. Competent in feature extraction and pattern recognition, deep …

Efficient evaluation methods for neural architecture search: A survey

X Song, X **e, Z Lv, GG Yen, W Ding, J Lv… - arxiv preprint arxiv …, 2023 - arxiv.org
Neural Architecture Search (NAS) has received increasing attention because of its
exceptional merits in automating the design of Deep Neural Network (DNN) architectures …