Radial Basis Function Networks for Convolutional Neural Networks to Learn Similarity Distance Metric and Improve Interpretability
This work addresses the problem of enhancing interpretability and similarity learning in computer vision models, though it appears incremental by adapting classical RBFs to modern CNNs.
The paper tackled the integration of radial basis function networks (RBFs) with convolutional neural networks (CNNs) to learn a similarity distance metric and improve interpretability in image classification, achieving successful application across various CNN architectures on benchmark datasets.
Radial basis function neural networks (RBFs) are prime candidates for pattern classification and regression and have been used extensively in classical machine learning applications. However, RBFs have not been integrated into contemporary deep learning research and computer vision using conventional convolutional neural networks (CNNs) due to their lack of adaptability with modern architectures. In this paper, we adapt RBF networks as a classifier on top of CNNs by modifying the training process and introducing a new activation function to train modern vision architectures end-to-end for image classification. The specific architecture of RBFs enables the learning of a similarity distance metric to compare and find similar and dissimilar images. Furthermore, we demonstrate that using an RBF classifier on top of any CNN architecture provides new human-interpretable insights about the decision-making process of the models. Finally, we successfully apply RBFs to a range of CNN architectures and evaluate the results on benchmark computer vision datasets.