Fig. 6: Comparison between the performance of efficiently fine-tuned CAMP and fully fine-tuned models.
From: CAMP: continuous and adaptive learning model in pathology
a The three configurations under consideration are task-specific, task-agnostic, and task-agnostic generative classification. b, d CAMP performs better than other considered methods in 16/17 patch-level datasets. The numbers in the bar show the gap between CAMP and the second-best competitors. c Comparison between CAMP and competitors in terms of the computation time and memory consumption during training and inference.
