动态调整学习顺序，让模型更适应不同设备的音频场景分类。
DDSC: Dynamic Dual-Signal Curriculum for Data-Efficient Acoustic Scene Classification under Domain Shift
- 根据模型进展和跨设备一致性动态调整训练数据权重
- 在有限标注下显著提升跨设备测试准确率，尤其对新设备效果明显
- 无需额外计算，可无缝集成到各类主流模型中
声学场景分类（ASC）在标签稀缺时易受设备差异导致的域偏移影响。现有基于课程的学习方法多采用静态排序或重加权策略，无法随模型学习过程动态调整。为此，本文提出动态双信号课程（DDSC），每轮训练中结合域不变性信号与学习进度信号，生成随时间变化的样本权重：初期优先学习跨设备一致的样本，后期逐步引入设备特异性样本。该方法轻量、与模型架构无关，且不增加推理开销。在DCASE 2024 Task 1官方评测协议下，DDSC在多种基线模型与标签预算设置下均稳定提升跨设备性能，尤其在未见设备测试集上表现最优。
原文摘要 · Abstract (English)
Acoustic scene classification (ASC) suffers from device-induced domain shift, especially when labels are limited. Prior work focuses on curriculum-based training schedules that structure data presentation by ordering or reweighting training examples from easy-to-hard to facilitate learning; however, existing curricula are static, fixing the ordering or the weights before training and ignoring that example difficulty and marginal utility evolve with the learned representation. To overcome this limitation, we propose the Dynamic Dual-Signal Curriculum (DDSC), a training schedule that adapts the curriculum online by combining two signals computed each epoch: a domain-invariance signal and a learning-progress signal. A time-varying scheduler fuses these signals into per-example weights that prioritize domain-invariant examples in early epochs and progressively emphasize device-specific cases. DDSC is lightweight, architecture-agnostic, and introduces no additional inference overhead. Under the official DCASE 2024 Task~1 protocol, DDSC consistently improves cross-device performance across diverse ASC baselines and label budgets, with the largest gains on unseen-device splits.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。