2 papers
cs.CV2026
Semantic Depth Matters: Explaining Errors of Deep Vision Networks through Perceived Class Similarities
Katarzyna Filus, MichaŠRomaszewski, Mateusz Żarski
Understanding deep neural network (DNN) behavior requires more than evaluating classification accuracy alone; analyzing errors and their predictability is equally crucial. Current…
cs.CV2025
Inspecting Training Dynamics of Similarity Development in Supervised Vision Networks
Katarzyna Filus, Mateusz Å»arski, 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…