KPCA-CAM: Visual Explainability of Deep Computer Vision Models using Kernel PCA

TL;DR

KPCA-CAM enhances the interpretability of CNNs in computer vision by using kernel PCA to generate more accurate class activation maps, providing clearer insights into model decision-making.

Contribution

This paper introduces KPCA-CAM, a novel method that applies kernel PCA to improve the quality of class activation maps in CNNs for better explainability.

Findings

KPCA-CAM produces more precise activation maps than existing CAM methods.

Empirical results on ILSVRC dataset show improved interpretability across CNN models.

The method offers deeper insights into CNN decision processes.

Abstract

Deep learning models often function as black boxes, providing no straightforward reasoning for their predictions. This is particularly true for computer vision models, which process tensors of pixel values to generate outcomes in tasks such as image classification and object detection. To elucidate the reasoning of these models, class activation maps (CAMs) are used to highlight salient regions that influence a model's output. This research introduces KPCA-CAM, a technique designed to enhance the interpretability of Convolutional Neural Networks (CNNs) through improved class activation maps. KPCA-CAM leverages Principal Component Analysis (PCA) with the kernel trick to capture nonlinear relationships within CNN activations more effectively. By mapping data into higher-dimensional spaces with kernel functions and extracting principal components from this transformed hyperplane, KPCA-CAM provides more accurate representations of the underlying data manifold. This enables a deeper understanding of the features influencing CNN decisions. Empirical evaluations on the ILSVRC dataset across different CNN models demonstrate that KPCA-CAM produces more precise activation maps, providing clearer insights into the model's reasoning compared to existing CAM algorithms. This research advances CAM techniques, equipping researchers and practitioners with a powerful tool to gain deeper insights into CNN decision-making processes and overall behaviors.