Variational Saccading: Efficient Inference for Large Resolution Images

12/08/2018
by   Jason Ramapuram, et al.
2

Image classification with deep neural networks is typically restricted to images of small dimensionality such as 224x244 in Resnet models. This limitation excludes the 4000x3000 dimensional images that are taken by modern smartphone cameras and smart devices. In this work, we aim to mitigate the prohibitive inferential and memory costs of operating in such large dimensional spaces. To sample from the high-resolution original input distribution, we propose using a smaller proxy distribution to learn the co-ordinates that correspond to regions of interest in the high-dimensional space. We introduce a new principled variational lower bound that captures the relationship of the proxy distribution's posterior and the original image's co-ordinate space in a way that maximizes the conditional classification likelihood. We empirically demonstrate on one synthetic benchmark and one real world large resolution DSLR camera image dataset that our method produces comparable results with 10x faster inference and lower memory consumption than a model that utilizes the entire original input distribution.

READ FULL TEXT

page 2

page 5

page 6

page 7

research
07/26/2022

Efficient High-Resolution Deep Learning: A Survey

Cameras in modern devices such as smartphones, satellites and medical eq...
research
07/01/2019

Radial Bayesian Neural Networks: Robust Variational Inference In Big Models

We propose Radial Bayesian Neural Networks: a variational distribution f...
research
09/09/2019

An Acceleration Framework for High Resolution Image Synthesis

Synthesis of high resolution images using Generative Adversarial Network...
research
04/19/2021

Improving Adversarial Robustness Using Proxy Distributions

We focus on the use of proxy distributions, i.e., approximations of the ...
research
12/08/2020

Out-Of-Distribution Detection With Subspace Techniques And Probabilistic Modeling Of Features

This paper presents a principled approach for detecting out-of-distribut...
research
08/31/2022

Injecting Image Details into CLIP's Feature Space

Although CLIP-like Visual Language Models provide a functional joint fea...

Please sign up or login with your details

Forgot password? Click here to reset