CNN Fixations: An unraveling approach to visualize the discriminative image regions
This addresses the problem of interpretability in CNNs for researchers and practitioners in computer vision, offering a generic tool for tasks like object recognition and caption generation, though it is incremental as it builds on existing visualization techniques.
The paper tackles the lack of transparency in deep convolutional neural networks (CNNs) by proposing a method to visualize discriminative image regions that guide predictions, achieving this without architectural changes or additional training.
Deep convolutional neural networks (CNN) have revolutionized various fields of vision research and have seen unprecedented adoption for multiple tasks such as classification, detection, captioning, etc. However, they offer little transparency into their inner workings and are often treated as black boxes that deliver excellent performance. In this work, we aim at alleviating this opaqueness of CNNs by providing visual explanations for the network's predictions. Our approach can analyze variety of CNN based models trained for vision applications such as object recognition and caption generation. Unlike existing methods, we achieve this via unraveling the forward pass operation. Proposed method exploits feature dependencies across the layer hierarchy and uncovers the discriminative image locations that guide the network's predictions. We name these locations CNN-Fixations, loosely analogous to human eye fixations. Our approach is a generic method that requires no architectural changes, additional training or gradient computation and computes the important image locations (CNN Fixations). We demonstrate through a variety of applications that our approach is able to localize the discriminative image locations across different network architectures, diverse vision tasks and data modalities.