提出两阶段方法，让迁移学习在少样本开放集识别中更有效。
Unlocking Transfer Learning for Open-World Few-Shot Recognition
- 先用感知开放集的元学习构建度量空间，再做无开放集干扰的迁移学习。
- 在miniImageNet和tieredImageNet上达最新性能，训练成本仅增1.5%。
- 适合需要处理未知类别、追求高效少样本识别的研究者。
少样本开放集识别（FSOSR）应对真实世界中关键挑战：将输入分类到已知类别（闭集类），同时识别超出这些类别的开放集输入。尽管迁移学习在闭世界中已成为主流范式，但其难以拓展至开放世界。为此，我们提出两阶段方法，包含感知开放集的元学习与无开放集干扰的迁移学习。在第一阶段，模型通过元学习建立度量空间，为后续阶段提供良好起点；第二阶段则通过迁移学习进一步适配具体目标任务。此外，我们引入策略，通过修改训练数据或生成伪开放集样本来模拟开放集样本。该方法在miniImageNet和tieredImageNet两个主流基准上取得当前最佳性能，且训练开销仅增加1.5%。本工作验证了迁移学习在FSOSR中的有效性。
原文摘要 · Abstract (English)
Few-Shot Open-Set Recognition (FSOSR) targets a critical real-world challenge, aiming to categorize inputs into known categories, termed closed-set classes, while identifying open-set inputs that fall outside these classes. Although transfer learning where a model is tuned to a given few-shot task has become a prominent paradigm in closed-world, we observe that it fails to expand to open-world. To unlock this challenge, we propose a two-stage method which consists of open-set aware meta-learning with open-set free transfer learning. In the open-set aware meta-learning stage, a model is trained to establish a metric space that serves as a beneficial starting point for the subsequent stage. During the open-set free transfer learning stage, the model is further adapted to a specific target task through transfer learning. Additionally, we introduce a strategy to simulate open-set examples by modifying the training dataset or generating pseudo open-set examples. The proposed method achieves state-of-the-art performance on two widely recognized benchmarks, miniImageNet and tieredImageNet, with only a 1.5\% increase in training effort. Our work demonstrates the effectiveness of transfer learning in FSOSR.
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。