paper-with-me

홈 › Papers

Stretchable Cells Help DARTS Search Better

2020-11-18 · Tao Huang, Shan You, Yibo Yang, Zhuozhuo Tu, Fei Wang, Chen Qian, ChangShui Zhang

Differentiable neural architecture search (DARTS) has gained much success in discovering flexible and diverse cell types. To reduce the evaluation gap, the supernet is expected to have identical layers with the target network. However, even for this consistent search, the searched cells often suffer from poor performance, especially for the supernet with fewer layers, as current DARTS methods are prone to wide and shallow cells, and this topology collapse induces sub-optimal searched cells. In this paper, we alleviate this issue by endowing the cells with explicit stretchability, so the search can be directly implemented on our stretchable cells for both operation type and topology simultaneously. Concretely, we introduce a set of topological variables and a combinatorial probabilistic distribution to explicitly model the target topology. With more diverse and complex topologies, our method adapts well for various layer numbers. Extensive experiments on CIFAR-10 and ImageNet show that our stretchable cells obtain better performance with fewer layers and parameters. For example, our method can improve DARTS by 0.28\% accuracy on CIFAR-10 dataset with 45\% parameters reduced or 2.9\% with similar FLOPs on ImageNet dataset.

📄 PDF Abstract BibTeX arXiv:2011.09300

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture Search

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

DartsReNet: Exploring new RNN cells in ReNet architectures

2023-04-11 · Brian Moser, Federico Raue, Jörn Hees, Andreas Dengel

We present new Recurrent Neural Network (RNN) cells for image classification using a Neural Architecture Search (NAS) approach called DARTS. We are interested in the ReNet architecture, which is a RNN based approach pres…

image-classificationImage ClassificationNeural Architecture Search

$μ$DARTS: Model Uncertainty-Aware Differentiable Architecture Search

2021-07-24 · Biswadeep Chakraborty, Saibal Mukhopadhyay

We present a Model Uncertainty-aware Differentiable ARchiTecture Search ($\mu$DARTS) that optimizes neural networks to simultaneously achieve high accuracy and low uncertainty. We introduce concrete dropout within DARTS …

modelNeural Architecture Search

EM-DARTS: Hierarchical Differentiable Architecture Search for Eye Movement Recognition

2024-09-22 · Huafeng Qin, Hongyu Zhu, Xin Jin, Xin Yu 외

Eye movement biometrics has received increasing attention thanks to its highly secure identification. Although deep learning (DL) models have shown success in eye movement recognition, their architectures largely rely on…

Neural Architecture Search

$Λ$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells

2022-10-14 · Sajad Movahedi, Melika Adabinejad, Ayyoob Imani, Arezou Keshavarz 외

Differentiable neural architecture search (DARTS) is a popular method for neural architecture search (NAS), which performs cell-search and utilizes continuous relaxation to improve the search efficiency via gradient-base…

Neural Architecture Search

SAR-NAS: Skeleton-based Action Recognition via Neural Architecture Searching

2020-10-29 · Haoyuan Zhang, Yonghong Hou, Pichao Wang, Zihui Guo 외

This paper presents a study of automatic design of neural network architectures for skeleton-based action recognition. Specifically, we encode a skeleton-based action instance into a tensor and carefully define a set of …

Action RecognitionSkeleton Based Action Recognition