What to Preserve, Where to Adapt: A Depth-Wise Analysis of Forgetting in Continual Gynecological Image Segmentation
Results show that forgetting depends not only on how much the model changes, but also on which parts of the model are allowed to change, which means that forgetting still increases as more blocks are trained and remains severe when the full backbone is updated.
Amal Saqib, Tausifa Jan Saleem, N. Saeed et al.
· 0 citations