FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

by   Alvin Wan, et al.

Differentiable Neural Architecture Search (DNAS) has demonstrated great success in designing state-of-the-art, efficient neural networks. However, DARTS-based DNAS's search space is small when compared to other search methods', since all candidate network layers must be explicitly instantiated in memory. To address this bottleneck, we propose a memory and computationally efficient DNAS variant: DMaskingNAS. This algorithm expands the search space by up to 10^14× over conventional DNAS, supporting searches over spatial and channel dimensions that are otherwise prohibitively expensive: input resolution and number of filters. We propose a masking mechanism for feature map reuse, so that memory and computational costs stay nearly constant as the search space expands. Furthermore, we employ effective shape propagation to maximize per-FLOP or per-parameter accuracy. The searched FBNetV2s yield state-of-the-art performance when compared with all previous architectures. With up to 421× less search cost, DMaskingNAS finds models with 0.9 higher accuracy, 15 accuracy but 20 outperforms MobileNetV3 by 2.6 FBNetV2 models are open-sourced at https://github.com/facebookresearch/mobile-vision.



There are no comments yet.


page 1

page 2

page 3

page 4


Fine-Grained Stochastic Architecture Search

State-of-the-art deep networks are often too large to deploy on mobile d...

MoViNets: Mobile Video Networks for Efficient Video Recognition

We present Mobile Video Networks (MoViNets), a family of computation and...

Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation

Recently, differentiable search methods have made major progress in redu...

Rethinking Bottleneck Structure for Efficient Mobile Network Design

The inverted residual block is dominating architecture design for mobile...

RADARS: Memory Efficient Reinforcement Learning Aided Differentiable Neural Architecture Search

Differentiable neural architecture search (DNAS) is known for its capaci...

Neural Architecture Search for Lightweight Non-Local Networks

Non-Local (NL) blocks have been widely studied in various vision tasks. ...

MemNet: Memory-Efficiency Guided Neural Architecture Search with Augment-Trim learning

Recent studies on automatic neural architectures search have demonstrate...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.