基于领域特定专家和原型分类器的域增量音频分类
Domain-incremental audio classification using domain-specific experts and prototype classifier
AI总结：
针对DCASE 2026挑战赛任务7，提出将域增量学习视为冻结特征重放问题，训练多个紧凑专家模型并冻结，最终用原型分类器聚合特征，通过生成式重放和跨阶段回归插补避免灾难性遗忘，在开发集上达到78.15%微观/77.03%宏观准确率。
摘要：
本技术报告介绍了DCASE 2026挑战赛任务7（域增量音频分类）的提交系统。主要障碍在于系统无法同时访问过去或未来领域的数据。我们将域增量学习（DIL）视为冻结特征重放问题。在每个增量阶段，训练一个或两个紧凑专家模型并保持固定；在最后阶段，将所有冻结专家的倒数第二层特征拼接起来，仅使用缓存的特征训练一个轻量级的每类原型分类器。这种设计通过在推理时保留每个专家模型来防止灾难性遗忘。为了在不存储原始音频的情况下保留早期领域知识，一些专家模型使用基于DeepInversion的生成式重放进行训练。训练了一个跨阶段回归插补器，用于填充早期阶段尚不存在的专家特征槽。我们提交了四个完全符合DIL要求的系统：三个基于不同冻结的五专家骨干网络的系统及其交叉堆叠集成，在开发集上实现了78.15%微观/77.03%宏观准确率，在两个评估指标上均优于每个单独的骨干网络。
英文摘要：
This technical report presents submission systems for Task 7(domain-incremental audio classification) of the DCASE 2026 Challenge. The main obstacle is that, the system is unable to access to past or future domain's data at once. We approached domain-incremental learning (DIL) as a frozen-feature replay problem. At each incremental stage, one or two compact experts are trained and then kept fixed; at the final stage, the penultimate features from all frozen experts are concatenated and used to train a lightweight per-class prototype classifier solely on cached features. This design prevents catastrophic forgetting by preserving each expert models at inference. To retain earlier-domain knowledge without storing raw audio, some experts were trained with DeepInversion-based generative replay. A cross-stage regression imputer was trained to fill the expert feature slots that did not yet exist at an ealier stage. We submit four fully DIL-compliant systems: three systems based on diverse frozen five-expert backbones and their cross-stack ensemble achieving 78.15% micro / 77.03% macro on the development set, outperforming every individual backbone on both evaluations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
