解决图像分类中持续学习时旧领域性能下降的问题。
Incremental Open-set Domain Adaptation
- 用生成模型从噪声中重建过往领域，构建伪源域
- 在新目标域上适配伪源域，缓解灾难性遗忘
- 适用于持续更新的开放集场景，如遥感图像识别
灾难性遗忘导致神经网络在连续学习视觉领域时性能下降。当训练新领域时，模型会因遗忘旧领域而表现变差。本文揭示了这一缺陷，并提出一种抗遗忘的增量学习策略。针对图像分类任务，首次定义了无监督增量开放集域适应（IOSDA）问题：每个目标域包含比源域更多的类别。模型按阶段处理领域流，推理时使用所有目标域的测试数据但不暴露其身份。为此，提出IOSDA-Net，一个两阶段学习框架：第一阶段通过生成框架从随机噪声中重构先前领域，形成伪源域；第二阶段将该伪源域适配至当前目标域。在Office-Home、DomainNet和新构建的光学遥感数据集UPRN-RSDA上进行了验证。
原文摘要 · Abstract (English)
Catastrophic forgetting makes neural network models unstable when learning visual domains consecutively. The neural network model drifts to catastrophic forgetting-induced low performance of previously learnt domains when training with new domains. We illuminate this current neural network model weakness and develop a forgetting-resistant incremental learning strategy. Here, we propose a new unsupervised incremental open-set domain adaptation (IOSDA) issue for image classification. Open-set domain adaptation adds complexity to the incremental domain adaptation issue since each target domain has more classes than the Source domain. In IOSDA, the model learns training with domain streams phase by phase in incremented time. Inference uses test data from all target domains without revealing their identities. We proposed IOSDA-Net, a two-stage learning pipeline, to solve the problem. The first module replicates prior domains from random noise using a generative framework and creates a pseudo source domain. In the second step, this pseudo source is adapted to the present target domain. We test our model on Office-Home, DomainNet, and UPRN-RSDA, a newly curated optical remote sensing dataset.
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。