通过训练时注入噪声，提升小样本图像模型在分布外数据上的泛化能力。
Noise Injection: Improving Out-of-Distribution Generalization for Limited Size Datasets
- 训练时加入高斯、泊松等基础噪声，迫使模型忽略设备特有伪影
- 分布内与分布外性能差距从0.10-0.20降至0.01-0.06
- 适合医疗影像等小样本、分布不稳场景下的模型鲁棒性提升
深度学习图像识别模型在跨设备、跨人群等分布外数据上表现不佳。以胸部X光片中的新冠检测为例，模型难以泛化到未在训练集中覆盖的新临床来源数据。这是因为模型倾向于学习源域特异性伪影而非可迁移的生物标志物，从而在分布内数据上取得高分。为增强模型对分布偏移的鲁棒性，本研究探索了在训练中引入高斯、散斑、泊松及椒盐噪声等基础噪声技术。实验结果表明，该方法能显著缩小分布内（ID）与分布外（OOD）评估间的性能差距，平均十次随机种子测试下，AUC、F1、准确率、召回率和特异性等关键指标的差距由0.10-0.20降至0.01-0.06。代码已公开于https://github.com/Duongmai127/Noisy-ood。
原文摘要 · Abstract (English)
Deep learned (DL) models for image recognition have been shown to fail to generalize to data from different devices, populations, etc. COVID-19 detection from Chest X-rays (CXRs), in particular, has been shown to fail to generalize to out-of-distribution (OOD) data from new clinical sources not covered in the training set. This occurs because models learn to exploit shortcuts - source-specific artifacts that do not translate to new distributions - rather than reasonable biomarkers to maximize performance on in-distribution (ID) data. Rendering the models more robust to distribution shifts, our study investigates the use of fundamental noise injection techniques (Gaussian, Speckle, Poisson, and Salt and Pepper) during training. Our empirical results demonstrate that this technique can significantly reduce the performance gap between ID and OOD evaluation from 0.10-0.20 to 0.01-0.06, based on results averaged over ten random seeds across key metrics such as AUC, F1, accuracy, recall and specificity. Our source code is publicly available at https://github.com/Duongmai127/Noisy-ood
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。