[2005.06305] Binarizing MobileNet via Evolution-based Searchingopen searchopen navigation menucontact arXivarXiv Twitter

Binary Neural Networks (BNNs), known to be one among the effectively compact network architectures, have achieved great outcomes in the visual tasks. Designing efficient binary architectures is not trivial due to the binary nature of the network. In this paper, we propose a use of evolutionary search to facilitate the construction and training scheme when binarizing MobileNet, a compact network with separable depth-wise convolution. Inspired by one-shot architecture search frameworks, we manipulate the idea of group convolution to design efficient 1-Bit Convolutional Neural Networks (CNNs), assuming an approximately optimal trade-off between computational cost and model accuracy. Our objective is to come up with a tiny yet efficient binary neural architecture by exploring the best candidates of the group convolution while optimizing the model performance in terms of complexity and latency. The approach is threefold. First, we train strong baseline binary networks with a wide range of r

1 mentions: @kuritateppei
Keywords: mobilenet
Date: 2020/05/19 02:21

Referring Tweets

@kuritateppei MobileNetをバイナリ化する。ただそのままバイナリ化するとDepth-wise convでの表現能力に限界があるので性能が出ない。なので代わりにGroup Convを採用し、そのGroup数を進化的に探索したのがキモ。最大FLOP数の制約を加え計算量とのトレードオフも制御可能。CVPR2020。 t.co/Q9iVa6LDZZ t.co/6ZkvlZeLhO

Related Entries

Read more [2005.02494] Mimicry: Towards the Reproducibility of GAN Researchopen searchopen navigation menucont...
0 users, 1 mentions 2020/05/09 00:52
Read more [1905.01684] Unsupervised Detection of Distinctive Regions on 3D Shapesopen searchopen navigation me...
0 users, 1 mentions 2020/05/15 00:52
Read more [2004.05439] Meta-Learning in Neural Networks: A Surveyopen searchopen navigation menucontact arXiva...
0 users, 2 mentions 2020/05/23 00:52
Read more albumentations.augmentations.transforms — albumentations 0.4.5 documentation
0 users, 1 mentions 2020/05/23 06:52
Read more [1704.00090] Learning to Predict Indoor Illumination from a Single Imageopen searchopen navigation m...
1 users, 1 mentions 2020/05/25 03:51