Characterizing and Taming Resolution in Convolutional Neural Networks

10/28/2021
by   Eddie Yan, et al.
8

Image resolution has a significant effect on the accuracy and computational, storage, and bandwidth costs of computer vision model inference. These costs are exacerbated when scaling out models to large inference serving systems and make image resolution an attractive target for optimization. However, the choice of resolution inherently introduces additional tightly coupled choices, such as image crop size, image detail, and compute kernel implementation that impact computational, storage, and bandwidth costs. Further complicating this setting, the optimal choices from the perspective of these metrics are highly dependent on the dataset and problem scenario. We characterize this tradeoff space, quantitatively studying the accuracy and efficiency tradeoff via systematic and automated tuning of image resolution, image quality and convolutional neural network operators. With the insights from this study, we propose a dynamic resolution mechanism that removes the need to statically choose a resolution ahead of time.

READ FULL TEXT

page 1

page 3

page 4

research
06/05/2021

Dynamic Resolution Network

Deep convolutional neural networks (CNNs) are often of sophisticated des...
research
09/17/2022

Understanding the Impact of Image Quality and Distance of Objects to Object Detection Performance

Deep learning has made great strides for object detection in images. The...
research
03/17/2021

Learning to Resize Images for Computer Vision Tasks

For all the ways convolutional neural nets have revolutionized computer ...
research
11/28/2016

Large-Scale Shape Retrieval with Sparse 3D Convolutional Neural Networks

In this paper we present results of performance evaluation of S3DCNN - a...
research
08/05/2019

Architecture-aware Network Pruning for Vision Quality Applications

Convolutional neural network (CNN) delivers impressive achievements in c...
research
08/24/2023

Data-Side Efficiencies for Lightweight Convolutional Neural Networks

We examine how the choice of data-side attributes for two important visu...
research
12/18/2018

The Prefetch Aggressiveness Tradeoff in 360^∘ Video Streaming

With 360^∘ video, only a limited fraction of the full view is displayed ...

Please sign up or login with your details

Forgot password? Click here to reset