提前预测领域迁移效果，选对模型和数据源
PAS: Estimating the target accuracy before domain adaptation
- 基于预训练特征嵌入评估源域与目标域的兼容性
- 在多个图像分类基准上预测准确率相关性显著
- 帮助高效选择最佳模型与源域，节省计算资源
领域适应的目标是利用来自不同但相关的源域的标注样本，对目标域的无标签样本进行预测。方法性能受源域选择和预训练特征提取器的影响很大，但由于缺乏目标域的标注验证集，且可用预训练模型数量庞大，选择变得困难。本文提出PAS，一种新型评分机制，可在实际进行领域适应前，估计源域数据集和预训练特征提取器对目标分类任务的可迁移性。PAS利用预训练模型的泛化能力，基于预训练特征嵌入评估源-目标兼容性。将其集成到框架中后，能有效识别出最相关的预训练模型和源域，从而提升目标域准确率并降低计算开销。在多个图像分类基准上的大量实验表明，PAS与实际目标准确率高度相关，并持续引导选择表现最佳的预训练模型与源域。
原文摘要 · Abstract (English)
The goal of domain adaptation is to make predictions for unlabeled samples from a target domain with the help of labeled samples from a different but related source domain. The performance of domain adaptation methods is highly influenced by the choice of source domain and pre-trained feature extractor. However, the selection of source data and pre-trained model is not trivial due to the absence of a labeled validation set for the target domain and the large number of available pre-trained models. In this work, we propose PAS, a novel score designed to estimate the transferability of a source domain set and a pre-trained feature extractor to a target classification task before actually performing domain adaptation. PAS leverages the generalization power of pre-trained models and assesses source-target compatibility based on the pre-trained feature embeddings. We integrate PAS into a framework that indicates the most relevant pre-trained model and source domain among multiple candidates, thus improving target accuracy while reducing the computational overhead. Extensive experiments on image classification benchmarks demonstrate that PAS correlates strongly with actual target accuracy and consistently guides the selection of the best-performing pre-trained model and source domain for adaptation.
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。