DeepAI
Log In Sign Up

Gaussian RAM: Lightweight Image Classification via Stochastic Retina-Inspired Glimpse and Reinforcement Learning

11/12/2020
by   Dongseok Shim, et al.
0

Previous studies on image classification have mainly focused on the performance of the networks, not on real-time operation or model compression. We propose a Gaussian Deep Recurrent visual Attention Model (GDRAM)- a reinforcement learning based lightweight deep neural network for large scale image classification that outperforms the conventional CNN (Convolutional Neural Network) which uses the entire image as input. Highly inspired by the biological visual recognition process, our model mimics the stochastic location of the retina with Gaussian distribution. We evaluate the model on Large cluttered MNIST, Large CIFAR-10 and Large CIFAR-100 datasets which are resized to 128 in both width and height.

READ FULL TEXT
06/04/2019

Visual Tree Convolutional Neural Network in Image Classification

In image classification, Convolutional Neural Network(CNN) models have a...
10/06/2018

Deep convolutional Gaussian processes

We propose deep convolutional Gaussian processes, a deep Gaussian proces...
04/15/2016

Latent Model Ensemble with Auto-localization

Deep Convolutional Neural Networks (CNN) have exhibited superior perform...
05/09/2018

Evaluating ResNeXt Model Architecture for Image Classification

In recent years, deep learning methods have been successfully applied to...
10/03/2020

TCLNet: Learning to Locate Typhoon Center Using Deep Neural Network

The task of typhoon center location plays an important role in typhoon i...
10/24/2022

Revisiting Sparse Convolutional Model for Visual Recognition

Despite strong empirical performance for image classification, deep neur...
06/26/2021

Image Classification with CondenseNeXt for ARM-Based Computing Platforms

In this paper, we demonstrate the implementation of our ultra-efficient ...

Code Repositories

gaussian-ram

Official PyTorch implementation of the paper: "Gaussian RAM: Lightweight Image Classification via Stochastic Retina Inspired Glimpse and Reinforcement Learning"


view repo