Decoding CNN based Object Classifier Using Visualization
This addresses the need for interpretability in CNN-based object classifiers for autonomous vehicle perception, but it is incremental as it applies existing visualization methods to this specific domain.
The paper tackles the problem of explaining how Convolutional Neural Networks (CNNs) work for object classification in autonomous vehicles by using visualization techniques to show feature extraction and activation heat maps, resulting in improved understanding of model accuracy and increased trust in object detection modules.
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.