ML Anthology

Classifier-Agnostic Saliency mAP Extraction

Konrad Zolna, Krzysztof J. Geras, Kyunghyun Cho
AAAI 2019 pp. 10087-10088
doi:10.1609/AAAI.V33I01.330110087 /aaai/2019/zolna2019aaai-classifier/

Abstract

Extracting saliency maps, which indicate parts of the image important to classification, requires many tricks to achieve satisfactory performance when using classifier-dependent methods. Instead, we propose classifier-agnostic saliency map extraction. This allows to find all parts of the image that any classifier could use, not just one given in advance. This way we extract much higher quality saliency maps.

PDF AAAI Semantic Scholar

Cite

Text

Zolna et al. "Classifier-Agnostic Saliency mAP Extraction." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.330110087

Markdown

[Zolna et al. "Classifier-Agnostic Saliency mAP Extraction." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/zolna2019aaai-classifier/) doi:10.1609/AAAI.V33I01.330110087

BibTeX

@inproceedings{zolna2019aaai-classifier,
  title     = {{Classifier-Agnostic Saliency mAP Extraction}},
  author    = {Zolna, Konrad and Geras, Krzysztof J. and Cho, Kyunghyun},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {10087-10088},
  doi       = {10.1609/AAAI.V33I01.330110087},
  url       = {https://mlanthology.org/aaai/2019/zolna2019aaai-classifier/}
}