Decoding CNN based Object Classifier Using Visualization

07/15/2020
by   Abhishek Mukhopadhyay, et al.
0

This paper investigates how working of Convolutional Neural Network (CNN) can be explained through visualization in the context of machine perception of autonomous vehicles. We visualize what type of features are extracted in different convolution layers of CNN that helps to understand how CNN gradually increases spatial information in every layer. Thus, it concentrates on region of interests in every transformation. Visualizing heat map of activation helps us to understand how CNN classifies and localizes different objects in image. This study also helps us to reason behind low accuracy of a model helps to increase trust on object detection module.

READ FULL TEXT
research
05/05/2019

A Review of Object Detection Models based on Convolutional Neural Network

Convolutional Neural Network (CNN) has become the state-of-the-art for o...
research
08/24/2016

Computer-Aided Colorectal Tumor Classification in NBI Endoscopy Using CNN Features

In this paper we report results for recognizing colorectal NBI endoscopi...
research
08/08/2020

Using PSPNet and UNet to analyze the internal parameter relationship and visualization of the convolutional neural network

Convolutional neural network(CNN) has achieved great success in many fie...
research
07/09/2015

Understanding Intra-Class Knowledge Inside CNN

Convolutional Neural Network (CNN) has been successful in image recognit...
research
05/07/2015

Object detection via a multi-region & semantic segmentation-aware CNN model

We propose an object detection system that relies on a multi-region deep...
research
10/15/2015

DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers

In this paper we evaluate the quality of the activation layers of a conv...
research
05/12/2021

A one-armed CNN for exoplanet detection from light curves

We propose Genesis, a one-armed simplified Convolutional Neural Network ...

Please sign up or login with your details

Forgot password? Click here to reset