Fig. 4: Lung nodule detection.
From: Dynamic memory to alleviate catastrophic forgetting in continual learning with medical imaging
Average precision (AP) measured on the validation set during training for DM and DM-PD with M = 128 as well as a random replacement memory and naive continual learning approach. The timeline at the bottom represents the changes of domains in the data stream. a As soon as Scanner F data occurred in the stream, the validation performed on the Scanner F (and also Scanner G) domain increased for all approaches. b A clear drop in performance (AP) occurred for the naive and random replacement approach for Scanner E, F and G, after some steps of training on Scanner H data, which marked catastrophic forgetting. For DM, the performance first dropped slightly, but recovered after some training steps, because samples from the memory are used for training. The DM-PD performance remained stable for Scanners E, F and G. c At the end of continual training, a better performance was achieved for Scanner E, F and G, when dynamic memory was utilized. For Scanner H, the performance for all three approaches was similar. d The performance for Scanner E was stable during the entire continual training process for all approaches, showing a base training that was saturated for scanner E.
