Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping (Student Abstract)

Kira Vinogradova, Alexandr Dibrov, Gene Myers

AAAI 2020 pp. 13943-13944

doi:10.1609/AAAI.V34I10.7244 /aaai/2020/vinogradova2020aaai-interpretable/

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.

PDF AAAI Semantic Scholar

Cite

Text

Vinogradova et al. "Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I10.7244

Markdown

[Vinogradova et al. "Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/vinogradova2020aaai-interpretable/) doi:10.1609/AAAI.V34I10.7244

BibTeX

@inproceedings{vinogradova2020aaai-interpretable,
  title     = {{Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping (Student Abstract)}},
  author    = {Vinogradova, Kira and Dibrov, Alexandr and Myers, Gene},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13943-13944},
  doi       = {10.1609/AAAI.V34I10.7244},
  url       = {https://mlanthology.org/aaai/2020/vinogradova2020aaai-interpretable/}
}