Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping (Student Abstract)
Kira Vinogradova, Alexandr Dibrov, Gene Myers
Abstract
Convolutional neural networks have become state-of-the-art in a wide range of image recognition tasks. The interpretation of their predictions, however, is an active area of research. Whereas various interpretation methods have been suggested for image classification, the interpretation of image segmentation still remains largely unexplored. To that end, we propose seg-grad-cam, a gradient-based method for interpreting semantic segmentation. Our method is an extension of the widely-used Grad-CAM method, applied locally to produce heatmaps showing the relevance of individual pixels for semantic segmentation.
Topics & Concepts
SegmentationArtificial intelligenceInterpretation (philosophy)Computer sciencePattern recognition (psychology)Class (philosophy)Convolutional neural networkImage (mathematics)PixelExtension (predicate logic)Relevance (law)Range (aeronautics)Image segmentationSemantic interpretationProgramming languageMaterials scienceLawPolitical scienceComposite materialExplainable Artificial Intelligence (XAI)Advanced Neural Network ApplicationsMachine Learning and Data Classification