Stretchable Cells Help DARTS Search Better
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Neural Architecture SearchMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DartsReNet: Exploring new RNN cells in ReNet architectures
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
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 SearchEM-DARTS: Hierarchical Differentiable Architecture Search for Eye Movement Recognition
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
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 SearchSAR-NAS: Skeleton-based Action Recognition via Neural Architecture Searching
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