无标签目标域下，用估计准确率校准模型置信度。
Calibration of Network Confidence for Unsupervised Domain Adaptation Using Estimated Accuracy
- 通过源域准确率推估目标域真实准确率，实现置信度校准。
- 在多个标准数据集上显著优于依赖重要性加权的方法。
- 适合需要可靠置信度的无监督域适应场景。
本研究解决在仅使用目标域无标签样本进行模型迁移时，如何校准网络置信度的问题。由于目标域缺乏标签，无法直接在目标域上校准模型。为此，我们提出一种基于估计网络在目标域准确率的校准方法：先计算模型在有标签源域上的准确率，再将其调整为反映目标域实际性能的估计值。通过最小化估计准确率与预测置信度之间的差异，直接在目标域上完成置信度校准。实验表明，该方法在多个标准数据集上显著优于依赖重要性加权的现有方法。
原文摘要 · Abstract (English)
This study addresses the problem of calibrating network confidence while adapting a model that was originally trained on a source domain to a target domain using unlabeled samples from the target domain. The absence of labels from the target domain makes it impossible to directly calibrate the adapted network on the target domain. To tackle this challenge, we introduce a calibration procedure that relies on estimating the network's accuracy on the target domain. The network accuracy is first computed on the labeled source data and then is modified to represent the actual accuracy of the model on the target domain. The proposed algorithm calibrates the prediction confidence directly in the target domain by minimizing the disparity between the estimated accuracy and the computed confidence. The experimental results show that our method significantly outperforms existing methods, which rely on importance weighting, across several standard datasets.
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。