paper-with-me

Papers

High performance ultra-low-precision convolutions on mobile devices

2017-12-06 · Andrew Tulloch, Yangqing Jia

Many applications of mobile deep learning, especially real-time computer vision workloads, are constrained by computation power. This is particularly true for workloads running on older consumer phones, where a typical device might be powered by a single- or dual-core ARMv7 CPU. We provide an open-source implementation and a comprehensive analysis of (to our knowledge) the state of the art ultra-low-precision (<4 bit precision) implementation of the core primitives required for modern deep learning workloads on ARMv7 devices, and demonstrate speedups of 4x-20x over our additional state-of-the-art float32 and int8 baselines.

📄 PDF Abstract BibTeX arXiv:1712.02427

Code (0)

등록된 구현이 없습니다.

Tasks

CPUDeep LearningVocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

UtVAA: Ultra-tiny Vision Transformer with Affix Attention for Mobile Image Classification

2026-06-02 · Romiyal George, Sathiyamohan Nishankar, Selvarajah Thuseethan, Roshan G. Ragel arxiv

Vision Transformers (ViTs) have demonstrated strong representation capability in image classification. However, their quadratic self-attention complexity and large parameter counts limit deployment on resource-constraine…

Image Classification

BANet: Bilateral Aggregation Network for Mobile Stereo Matching

2025-03-05 · Gangwei Xu, Jiaxin Liu, Xianqi Wang, Junda Cheng 외

State-of-the-art stereo matching methods typically use costly 3D convolutions to aggregate a full cost volume, but their computational demands make mobile deployment challenging. Directly applying 2D convolutions for cos…

Stereo Matching

Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks

2022-03-08 · Yunshan Zhong, Mingbao Lin, Xunchao Li, Ke Li 외

Light-weight super-resolution (SR) models have received considerable attention for their serviceability in mobile devices. Many efforts employ network quantization to compress SR models. However, these methods suffer fro…

QuantizationSuper-Resolution

MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

2020-04-30 · CVPR 2021 1 · Yunyang Xiong, Hanxiao Liu, Suyog Gupta, Berkin Akin 외

Inverted bottleneck layers, which are built upon depthwise convolutions, have been the predominant building blocks in state-of-the-art object detection models on mobile devices. In this work, we investigate the optimalit…

CPUGPUNeural Architecture SearchObject+2

AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks

2021-04-15 · Haojin Yang, Zhen Shen, Yucheng Zhao

Deep convolutional neural networks (CNN) have achieved astonishing results in a large variety of applications. However, using these models on mobile or embedded devices is difficult due to the limited memory and computat…

Image Classification