Blur-CAM: visual interpretation of deep convolutional networks based on Gaussian fuzzy

As deep learning continues to advance, the complexity of its network structures has also increased. The application of visualization techniques to elucidate the learning mechanisms of deep convolutional neural networks constitutes a crucial aspect of research in interpretable artificial intelligence and the field of deep learning. Numerous visualization methods have emerged to interpret these black-box architectures, enabling analysis and comprehension of internal decision-making processes. In this paper, we introduce Blur-CAM, a method that employs Gaussian blur to process both masked and unmasked regions, enhancing object understanding and providing smoother optimization transitions for object localization in images. We evaluate our approach on the ILSVRC 2012 and PASCAL VOC 2012 datasets, achieving commendable results.