4 papers
Sparse Autoencoders Can Induce Local Geometry for Mitigating Catastrophic Forgetting
Kamil Faber, Katarzyna Filus, Łukasz Pawela
Catastrophic forgetting remains a challenge in supervised continual learning, as adapting to new tasks causes representation drift and loss of previously learned information. This…
Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
Katarzyna Filus, Kamil Faber, Roberto Corizzo +1
Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catas…
Inspecting Training Dynamics of Similarity Development in Supervised Vision Networks
Katarzyna Filus, Mateusz Żarski
For trustworthy and human-aware artificial intelligence, models should be evaluated beyond accuracy, among others through error predictability and semantic alignment. Similarity is…
Semantic Depth Matters: Explaining Errors of Deep Vision Networks through Perceived Class Similarities
Katarzyna Filus, Michał Romaszewski, Mateusz Żarski
Understanding deep neural network (DNN) behavior requires more than evaluating classification accuracy alone; analyzing errors and their predictability is equally crucial. Current…