paper-with-me

Papers

Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours

2019-04-05 · Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu

Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the runtime constraint of a mobile device? Neural architecture search (NAS) has revolutionized the design of hardware-efficient ConvNets by automating this process. However, the NAS problem remains challenging due to the combinatorially large design space, causing a significant searching time (at least 200 GPU-hours). To alleviate this complexity, we propose Single-Path NAS, a novel differentiable NAS method for designing hardware-efficient ConvNets in less than 4 hours. Our contributions are as follows: 1. Single-path search space: Compared to previous differentiable NAS methods, Single-Path NAS uses one single-path over-parameterized ConvNet to encode all architectural decisions with shared convolutional kernel parameters, hence drastically decreasing the number of trainable parameters and the search cost down to few epochs. 2. Hardware-efficient ImageNet classification: Single-Path NAS achieves 74.96% top-1 accuracy on ImageNet with 79ms latency on a Pixel 1 phone, which is state-of-the-art accuracy compared to NAS methods with similar constraints (<80ms). 3. NAS efficiency: Single-Path NAS search cost is only 8 epochs (30 TPU-hours), which is up to 5,000x faster compared to prior work. 4. Reproducibility: Unlike all recent mobile-efficient NAS methods which only release pretrained models, we open-source our entire codebase at: https://github.com/dstamoulis/single-path-nas.

📄 PDF Abstract BibTeX arXiv:1904.02877

Code (9)

dstamoulis/single-path-nas 공식 구현 tf
2023-MindSpore-4/Code11/tree/main/single_path_nas mindspore
2023-MindSpore-4/Code7/tree/main/single_path_nas mindspore
Mind23-2/MindCode-64 mindspore
Mind23-2/MindCode-88/tree/main/single_path_nas mindspore
code-implementation1/Code8/tree/main/single_path_nas mindspore
cogsys-tuebingen/uninas pytorch
mindspore-ai/models/tree/master/research/cv/single_path_nas mindspore
osmr/imgclsmob mxnet

Tasks

General ClassificationGPUimage-classificationImage ClassificationNeural Architecture Search

Methods 이 논문이 사용한 방법론

Differentiable NAS 설명 없음
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Similar Papers 제목 키워드 기반

Single-Path NAS: Device-Aware Efficient ConvNet Design

2019-05-10 · Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos 외

Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device? Neural Architecture Search (NAS) for ConvNet design is a chall…

General ClassificationGPUimage-classificationImage Classification+1

Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization

2019-07-01 · Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos 외

Can we reduce the search cost of Neural Architecture Search (NAS) from days down to only few hours? NAS methods automate the design of Convolutional Networks (ConvNets) under hardware constraints and they have emerged as…

AutoMLGPUHyperparameter Optimizationimage-classification+2

Designing Concise ConvNets with Columnar Stages

2024-10-05 · Ashish Kumar, Jaesik Park

In the era of vision Transformers, the recent success of VanillaNet shows the huge potential of simple and concise convolutional neural networks (ConvNets). Where such models mainly focus on runtime, it is also crucial t…

MinConvNets: A new class of multiplication-less Neural Networks

2021-01-23 · Xuecan Yang, Sumanta Chaudhuri, Laurence Likforman, Lirida Naviner

Convolutional Neural Networks have achieved unprecedented success in image classification, recognition, or detection applications. However, their large-scale deployment in embedded devices is still limited by the huge co…

image-classificationImage ClassificationTransfer Learning

Efficient ConvNets for Analog Arrays

2018-07-03 · Malte J. Rasch, Tayfun Gokmen, Mattia Rigotti, Wilfried Haensch

Analog arrays are a promising upcoming hardware technology with the potential to drastically speed up deep learning. Their main advantage is that they compute matrix-vector products in constant time, irrespective of the …