CompactNet: Platform-Aware Automatic Optimization for Convolutional Neural Networks

2019-05-28 · Weicheng Li, Rui Wang, Zhongzhi Luan, Di Huang, Zidong Du, Yunji Chen, Depei Qian

Convolutional Neural Network (CNN) based Deep Learning (DL) has achieved great progress in many real-life applications. Meanwhile, due to the complex model structures against strict latency and memory restriction, the implementation of CNN models on the resource-limited platforms is becoming more challenging. This work proposes a solution, called CompactNet\footnote{Project URL: \url{https://github.com/CompactNet/CompactNet}}, which automatically optimizes a pre-trained CNN model on a specific resource-limited platform given a specific target of inference speedup. Guided by a simulator of the target platform, CompactNet progressively trims a pre-trained network by removing certain redundant filters until the target speedup is reached and generates an optimal platform-specific model while maintaining the accuracy. We evaluate our work on two platforms of a mobile ARM CPU and a machine learning accelerator NPU (Cambricon-1A ISA) on a Huawei Mate10 smartphone. For the state-of-the-art slim CNN model made for the embedded platform, MobileNetV2, CompactNet achieves up to a 1.8x kernel computation speedup with equal or even higher accuracy for image classification tasks on the Cifar-10 dataset.

📄 PDF Abstract BibTeX arXiv:1905.11669

Code (1)

CompactNet/CompactNet 공식 구현 tf

Tasks

CPUimage-classification Image Classification

Methods 이 논문이 사용한 방법론

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…

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,…

Batch Normalization 설명 없음

Inverted Residual Block 설명 없음

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

An affordable hardware-aware neural architecture search for deploying convolutional neural networks on ultra-low-power computing platforms

2026-06-15 · Andrea Mattia Garavagno, Edoardo Ragusa, Antonio Frisoli, Paolo Gastaldo arxiv

Hardware-aware neural architecture search (HW-NAS) allows the integration of Convolutional Neural Networks (CNNs) in microcontrollers devices by automatically designing neural architectures that can fit prearranged hardw…

Neural Architecture Search

OpEvo: An Evolutionary Method for Tensor Operator Optimization

2020-06-10 · Xiaotian Gao, Cui Wei, Lintao Zhang, Mao Yang

Training and inference efficiency of deep neural networks highly rely on the performance of tensor operators on hardware platforms. Manually optimizing tensor operators has limitations in terms of supporting new operator…

ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation

2018-12-21 · CVPR 2019 6 · Xiaoliang Dai, Peizhao Zhang, Bichen Wu, Hongxu Yin 외

This paper proposes an efficient neural network (NN) architecture design methodology called Chameleon that honors given resource constraints. Instead of developing new building blocks or using computationally-intensive r…

Bayesian Optimization CPU Efficient Neural Network GPU+2

AP-DRL: A Synergistic Algorithm-Hardware Framework for Automatic Task Partitioning of Deep Reinforcement Learning on Versal ACAP

2026-03-31 · Enlai Li, Zhe Lin, Sharad Sinha, Wei Zhang arxiv

Deep reinforcement learning has demonstrated remarkable success across various domains. However, the tight coupling between training and inference processes makes accelerating DRL training an essential challenge for DRL …

Reinforcement Learning

HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks

2023-01-20 · Jinqi Xiao, Chengming Zhang, Yu Gong, Miao Yin 외

Low-rank compression is an important model compression strategy for obtaining compact neural network models. In general, because the rank values directly determine the model complexity and model accuracy, proper selectio…

GPU Low-rank compression Model Compression