paper-with-me

Papers

EC-DARTS: Inducing Equalized and Consistent Optimization Into DARTS

2021-01-01 · ICCV 2021 10 · Qinqin Zhou, Xiawu Zheng, Liujuan Cao, Bineng Zhong, Teng Xi, Gang Zhang, Errui Ding, Mingliang Xu, Rongrong Ji

Based on the relaxed search space, differential architecture search (DARTS) is efficient in searching for a high-performance architecture. However, the unbalanced competition among operations that have different trainable parameters causes the model collapse. Besides, the inconsistent structures in the search and retraining stages causes cross-stage evaluation to be unstable. In this paper, we call these issues as an operation gap and a structure gap in DARTS. To shrink these gaps, we propose to induce equalized and consistent optimization in differentiable architecture search (EC-DARTS). EC-DARTS decouples different operations based on their categories to optimize the operation weights so that the operation gap between them is shrinked. Besides, we introduce an induced structural transition to bridge the structure gap between the model structures in the search and retraining stages. Extensive experiments on CIFAR10 and ImageNet demonstrate the effectiveness of our method. Specifically, on CIFAR10, we achieve a test error of 2.39%, while only 0.3 GPU days on NVIDIA TITAN V. On ImageNet, our method achieves a top-1 error of 23.6% under the mobile setting.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

GPU

Methods 이 논문이 사용한 방법론

DARTS Differentiable Architecture Search (DART) is a method for efficient architecture search. The search space is made continuous so that the architecture can be optimized with…

Similar Papers 제목 키워드 기반

Hierarchical Neural Architecture Search via Operator Clustering

2019-09-26 · Guilin Li, Xing Zhang, Zitong Wang, Matthias Tan 외

Recently, the efficiency of automatic neural architecture design has been significantly improved by gradient-based search methods such as DARTS. However, recent literature has brought doubt to the generalization ability …

ClusteringNeural Architecture Search

Efficient Architecture Search via Bi-level Data Pruning

2023-12-21 · Chongjun Tu, Peng Ye, Weihao Lin, Hancheng Ye 외

Improving the efficiency of Neural Architecture Search (NAS) is a challenging but significant task that has received much attention. Previous works mainly adopted the Differentiable Architecture Search (DARTS) and improv…

Neural Architecture Search

LP-NAS: Linear Programming-based Neural Architecture Search

2026-08-14 · Abhishek Shukla, Ankur Sinha, Faiz Hamid arxiv

Neural Architecture Search (NAS) aims to automate neural network architecture design, reducing reliance on human expertise. Among the various NAS methods, differentiable NAS has gained prominence due to its efficiency an…

Neural Architecture Search

sharpDARTS: Faster and More Accurate Differentiable Architecture Search

2019-03-23 · Andrew Hundt, Varun Jain, Gregory D. Hager

Neural Architecture Search (NAS) has been a source of dramatic improvements in neural network design, with recent results meeting or exceeding the performance of hand-tuned architectures. However, our understanding of ho…

Hyperparameter OptimizationImage ClassificationNeural Architecture Search

Single-DARTS: Towards Stable Architecture Search

2021-08-18 · Pengfei Hou, Ying Jin, Yukang Chen

Differentiable architecture search (DARTS) marks a milestone in Neural Architecture Search (NAS), boasting simplicity and small search costs. However, DARTS still suffers from frequent performance collapse, which happens…

Neural Architecture Search