Decoding CNN based Object Classifier Using Visualization

TL;DR

This paper explores how visualization techniques can explain CNN-based object classifiers, revealing feature extraction processes and aiding in understanding and improving model accuracy for autonomous vehicle perception.

Contribution

It introduces visualization methods to interpret CNN features and localization, enhancing understanding of model decisions and identifying reasons for low accuracy.

Findings

Visualization reveals feature extraction at different CNN layers.

Heat maps help understand object localization.

Insights can improve trust and accuracy in object detection.

Abstract

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.