Domain Adversarial RetinaNet as a Reference Algorithm for the MItosis DOmain Generalization Challenge. (arXiv:2108.11269v2 [eess.IV] UPDATED)

Assessing the Mitotic Count has a known high degree of intra- and inter-rater
variability. Computer-aided systems have proven to decrease this variability
and reduce labeling time. These systems, however, are generally highly
dependent on their training domain and show poor applicability to unseen
domains. In histopathology, these domain shifts can result from various
sources, including different slide scanning systems used to digitize histologic
samples. The MItosis DOmain Generalization challenge focused on this specific
domain shift for the task of mitotic …

algorithm arxiv reference