发表机构
Tampere University（坦佩雷大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对声音事件分类的类增量学习，提出冻结特征提取器并微调动态头部分类器，有效缓解灾难性遗忘，兼顾稳定性与可塑性。
AI 中文摘要
本研究探讨了在声音事件分类任务的类增量学习场景中，防止灾难性遗忘的多种方法。我们利用FSD50K和AudioSet数据集，通过架构方法和正则化方法分析该问题。我们设计了增量阶段和解决方案，选择性保护网络内核免受权重更新影响以防止灾难性遗忘，并设计了一种动态头部解决方案，在每次学习新任务时自动扩展自身。研究结果表明，灾难性遗忘主要发生在较深层，尤其是分类器头部。对于所研究的域内声音分类问题，最能缓解灾难性遗忘且最高效的解决方案是完全冻结特征提取器并对动态头部分类器进行微调，该方法表现出极少甚至无遗忘、良好的训练稳定性，并在记忆稳定性与学习可塑性之间取得了良好平衡。
英文摘要
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 the classifier head. For the studied in-domain sound classification problem, 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.
CommentsAccepted in MMSP2026
