MetaCAM: Ensemble-Based Class Activation Map
This addresses the need for trustworthy explanations in high-criticality fields like medicine and biometric identification, though it is incremental as it builds on existing CAM methods.
The paper tackled the problem of unreliable visual explanations from individual Class Activation Map (CAM) methods by proposing MetaCAM, an ensemble-based approach that combines multiple CAMs based on consensus of top-k% activated pixels, which improved ROAD performance to 0.393 compared to individual CAMs ranging from -0.101 to 0.172.
The need for clear, trustworthy explanations of deep learning model predictions is essential for high-criticality fields, such as medicine and biometric identification. Class Activation Maps (CAMs) are an increasingly popular category of visual explanation methods for Convolutional Neural Networks (CNNs). However, the performance of individual CAMs depends largely on experimental parameters such as the selected image, target class, and model. Here, we propose MetaCAM, an ensemble-based method for combining multiple existing CAM methods based on the consensus of the top-k% most highly activated pixels across component CAMs. We perform experiments to quantifiably determine the optimal combination of 11 CAMs for a given MetaCAM experiment. A new method denoted Cumulative Residual Effect (CRE) is proposed to summarize large-scale ensemble-based experiments. We also present adaptive thresholding and demonstrate how it can be applied to individual CAMs to improve their performance, measured using pixel perturbation method Remove and Debias (ROAD). Lastly, we show that MetaCAM outperforms existing CAMs and refines the most salient regions of images used for model predictions. In a specific example, MetaCAM improved ROAD performance to 0.393 compared to 11 individual CAMs with ranges from -0.101-0.172, demonstrating the importance of combining CAMs through an ensembling method and adaptive thresholding.