paper-with-me

Papers

A Quantization-Friendly Separable Convolution for MobileNets

2018-03-22 · Tao Sheng, Chen Feng, Shaojie Zhuo, Xiaopeng Zhang, Liang Shen, Mickey Aleksic

As deep learning (DL) is being rapidly pushed to edge computing, researchers invented various ways to make inference computation more efficient on mobile/IoT devices, such as network pruning, parameter compression, and etc. Quantization, as one of the key approaches, can effectively offload GPU, and make it possible to deploy DL on fixed-point pipeline. Unfortunately, not all existing networks design are friendly to quantization. For example, the popular lightweight MobileNetV1, while it successfully reduces parameter size and computation latency with separable convolution, our experiment shows its quantized models have large accuracy gap against its float point models. To resolve this, we analyzed the root cause of quantization loss and proposed a quantization-friendly separable convolution architecture. By evaluating the image classification task on ImageNet2012 dataset, our modified MobileNetV1 model can archive 8-bit inference top-1 accuracy in 68.03%, almost closed the gap to the float pipeline.

📄 PDF Abstract BibTeX arXiv:1803.08607

Code (1)

pinto0309/onnx2tf tf

Tasks

Edge-computingGPUimage-classificationImage ClassificationNetwork PruningQuantization

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…
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,…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Subtensor Quantization for Mobilenets

2020-11-04 · Thu Dinh, Andrey Melnikov, Vasilios Daskalopoulos, Sek Chai

Quantization for deep neural networks (DNN) have enabled developers to deploy models with less memory and more efficient low-power inference. However, not all DNN designs are friendly to quantization. For example, the po…

image-classificationImage ClassificationQuantization

Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics

2021-04-24 · Stone Yun, Alexander Wong

As the "Mobile AI" revolution continues to grow, so does the need to understand the behaviour of edge-deployed deep neural networks. In particular, MobileNets are the go-to family of deep convolutional neural networks (C…

AllQuantization

Ternary MobileNets via Per-Layer Hybrid Filter Banks

2019-11-04 · Dibakar Gope, Jesse Beu, Urmish Thakker, Matthew Mattina

MobileNets family of computer vision neural networks have fueled tremendous progress in the design and organization of resource-efficient architectures in recent years. New applications with stringent real-time requireme…

Quantization

PydMobileNet: Improved Version of MobileNets with Pyramid Depthwise Separable Convolution

2018-11-17 · Van-Thanh Hoang, Kang-Hyun Jo

Convolutional neural networks (CNNs) have shown remarkable performance in various computer vision tasks in recent years. However, the increasing model size has raised challenges in adopting them in real-time applications…

Object Recognition

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

2017-04-17 · Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko 외

We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight d…

geo-localizationImage StitchingObject Detection