AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling

Abstract

Neural architecture search (NAS) has shown great promise in designing state-of-the-art (SOTA) models that are both accurate and efficient. Recently, two-stage NAS, e.g. BigNAS, decouples the model training and searching process and achieves remarkable search efficiency and accuracy. Two-stage NAS requires sampling from the search space during training, which directly impacts the accuracy of the final searched models. While uniform sampling has been widely used for its simplicity, it is agnostic of the model performance Pareto front, which is the main focus in the search process, and thus, misses opportunities to further improve the model accuracy. In this work, we propose AttentiveNAS that focuses on improving the sampling strategy to achieve better performance Pareto. We also propose algorithms to efficiently and effectively identify the networks on the Pareto during training. Without extra re-training or post-processing, we can simultaneously obtain a large number of networks across a wide range of FLOPs. Our discovered model family, AttentiveNAS models, achieves top-1 accuracy from 77.3% to 80.7% on ImageNet, and outperforms SOTA models, including BigNAS and Once-for-All networks. We also achieve ImageNet accuracy of 80.1% with only 491 MFLOPs. Our training code and pretrained models are available at https://github.com/facebookresearch/AttentiveNAS.

arXiv comment2021 Conference on Computer Vision and Pattern Recognition

References in corpus (11)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Neural Architecture Search with Reinforcement Learning
• AutoAugment: Learning Augmentation Policies from Data
• Efficient Neural Architecture Search via Parameter Sharing
• NAS-Bench-101: Towards Reproducible Neural Architecture Search
• NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search
• BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models
• MaxUp: A Simple Way to Improve Generalization of Neural Network Training
• Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search
• FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining

Cited by in corpus (4)

• Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
• AlphaNet: Improved Training of Supernets with Alpha-Divergence
• AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergence
• Reconsidering CO2 emissions from Computer Vision