Investigating catastrophic forgetting in sound event classification
Quick summary
arXiv:2609.11447v1 Announce Type: cross Abstract: 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 ma
Key takeaways
- arXiv:2609.11447v1 Announce Type: cross Abstract: 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.
Why it matters
The importance of “Investigating catastrophic forgetting in sound event classification” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments