On the stability, correctness and plausibility of visual explanation methods based on feature importance

Romain Xu-Darme, Jenny Benois-Pineau, Romain Giot, Georges Quénot, Zakaria Chihani, Marie-Christine Rousset, Alexey Zhukov. On the stability, correctness and plausibility of visual explanation methods based on feature importance. In Aladine Chetouani, Werner Bailer, Cathal Gurrin, Alexandre Benoît, editors, 20th International Conference on Content-based Multimedia Indexing, CBMI 2023, Orleans, France, September 20-22, 2023. pages 119-125, ACM, 2023. [doi]

@inproceedings{Xu-DarmeBGQCRZ23,
  title = {On the stability, correctness and plausibility of visual explanation methods based on feature importance},
  author = {Romain Xu-Darme and Jenny Benois-Pineau and Romain Giot and Georges Quénot and Zakaria Chihani and Marie-Christine Rousset and Alexey Zhukov},
  year = {2023},
  doi = {10.1145/3617233.3617257},
  url = {https://doi.org/10.1145/3617233.3617257},
  researchr = {https://researchr.org/publication/Xu-DarmeBGQCRZ23},
  cites = {0},
  citedby = {0},
  pages = {119-125},
  booktitle = {20th International Conference on Content-based Multimedia Indexing, CBMI 2023, Orleans, France, September 20-22, 2023},
  editor = {Aladine Chetouani and Werner Bailer and Cathal Gurrin and Alexandre Benoît},
  publisher = {ACM},
}