Alert button
Picture for Alexandr Dibrov

Alexandr Dibrov

Alert button

Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping

Feb 26, 2020
Kira Vinogradova, Alexandr Dibrov, Gene Myers

Figure 1 for Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping
Figure 2 for Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping

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.

* Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, New York, USA, Feb 2020  
* 2 pages, 2 figures. AAAI 2020 camera-ready 
Viaarxiv icon