SOURCE-LINKED INTELLIGENCE

Investigating catastrophic forgetting in sound event classification

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

This work investigates a number of approaches to prevent catastrophic forgetting in class incremental learning scenarios for sound event classification tasks. We analyze the problem using architectural and regularization approaches, using FSD50K and AudioSet datasets. We design incremental stages and solutions that selectively protect the kernels of the network from weight updates to prevent catastrophic forgetting, and a dynamic head solution that expands itself each time a new task is learned. The findings show that catastrophic forgetting mainly happens in deeper layers, in particular in th

Read original source ↗ Open in workspace

recordType

paper

region

Global