3 papers
cs.LG2025
Predicting the Susceptibility of Examples to Catastrophic Forgetting
Guy Hacohen, Tinne Tuytelaars
Catastrophic forgetting - the tendency of neural networks to forget previously learned data when learning new information - remains a central challenge in continual learning. In th…
cs.LG2025
Active Learning with a Noisy Annotator
Netta Shafir, Guy Hacohen, Daphna Weinshall
Active Learning (AL) aims to reduce annotation costs by strategically selecting the most informative samples for labeling. However, most active learning methods struggle in the low…
cs.LG2025
Same accuracy, twice as fast: continuous training surpasses retraining from scratch
Eli Verwimp, Guy Hacohen, Tinne Tuytelaars
Continual learning aims to enable models to adapt to new datasets without losing performance on previously learned data, often assuming that prior data is no longer available. Howe…