通过优化参数选择提升持续学习性能，简单有效。
Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need
- 设计GMC与DFR实现高效领域数据存储与平衡
- 多层级特征融合网络增强领域特征提取能力
- 适配多种高效微调方法，适用于多任务场景
深度神经网络在动态现实环境中常因数据分布随时间变化而性能下降。领域增量学习（DIL）通过持续模型适应提供解决方案，其中参数隔离式DIL（PIDIL）因其减少知识冲突的潜力成为主流范式。然而，现有方法在领域数量和类别增多时，参数选择精度显著下降。为此，我们提出SOYO——一种轻量级框架，通过高斯混合压缩器（GMC）与领域特征重采样器（DFR）高效存储并平衡先验领域数据，结合多层级领域特征融合网络（MDFN）强化特征提取。该框架支持多种参数高效微调（PEFT）方法，并在图像分类、目标检测与语音增强等任务上验证其有效性。六项基准测试结果表明，SOYO在复杂演化环境中持续优于现有基线，展现强大鲁棒性与适应性。代码将发布于 https://github.com/qwangcv/SOYO。
原文摘要 · Abstract (English)
Deep neural networks (DNNs) often underperform in real-world, dynamic settings where data distributions change over time. Domain Incremental Learning (DIL) offers a solution by enabling continual model adaptation, with Parameter-Isolation DIL (PIDIL) emerging as a promising paradigm to reduce knowledge conflicts. However, existing PIDIL methods struggle with parameter selection accuracy, especially as the number of domains and corresponding classes grows. To address this, we propose SOYO, a lightweight framework that improves domain selection in PIDIL. SOYO introduces a Gaussian Mixture Compressor (GMC) and Domain Feature Resampler (DFR) to store and balance prior domain data efficiently, while a Multi-level Domain Feature Fusion Network (MDFN) enhances domain feature extraction. Our framework supports multiple Parameter-Efficient Fine-Tuning (PEFT) methods and is validated across tasks such as image classification, object detection, and speech enhancement. Experimental results on six benchmarks demonstrate SOYO's consistent superiority over existing baselines, showcasing its robustness and adaptability in complex, evolving environments. The codes will be released in https://github.com/qwangcv/SOYO.
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。