Annamaria Mesaros

The solution that seems to alleviate catastrophic forgetting and is the most efficient is a full freezing of the feature extractor with a fine-tuning of the dynamic head classifier, showing little to no forgetting and great training stability, and a good balance between memory-stability and learning plasticity.

Importance weighting can dramatically narrow the performance gap in audio classification evaluations, even with limited labeled data.

Learning sound classes across varying acoustic domains without prior data access reveals a critical gap in current incremental learning approaches.

Hebbian learning, often relegated to theory, can actually boost accuracy and stability in incremental audio classification tasks by selectively tuning network kernels.