Limitations of CNNs for Approximating the Ideal Observer Despite Quantity of Training Data or Depth of Network

Khalid Omer, Luca Caucci, Meredith K. Kupinski. Limitations of CNNs for Approximating the Ideal Observer Despite Quantity of Training Data or Depth of Network. In Charles A. Bouman, Gregery T. Buzzard, Robert L. Stevenson, editors, Computational Imaging XIX, Virtual Event, 11-28 January 2021. Ingenta, 2021. [doi]

@inproceedings{OmerCK21,
  title = {Limitations of CNNs for Approximating the Ideal Observer Despite Quantity of Training Data or Depth of Network},
  author = {Khalid Omer and Luca Caucci and Meredith K. Kupinski},
  year = {2021},
  doi = {10.2352/J.ImagingSci.Technol.2020.64.6.060408},
  url = {https://doi.org/10.2352/J.ImagingSci.Technol.2020.64.6.060408},
  researchr = {https://researchr.org/publication/OmerCK21},
  cites = {0},
  citedby = {0},
  booktitle = {Computational Imaging XIX, Virtual Event, 11-28 January 2021},
  editor = {Charles A. Bouman and Gregery T. Buzzard and Robert L. Stevenson},
  publisher = {Ingenta},
}