通过扰动特征空间提升模型迁移能力评估精度
Feature Space Perturbation: A Panacea to Enhanced Transferability Estimation
- 引入特征空间扰动，增强迁移性评估的鲁棒性
- 在LogMe上性能提升28.84%，验证方法有效性
- 适合需要精准筛选预训练模型的研究者使用
利用迁移性评估指标可从一组预训练模型中选出最适合下游任务的模型。现有方法主要关注目标数据集中特征嵌入与标签间的统计关系，却忽略了模型鲁棒性这一关键因素，限制了评估准确性。为此，本文提出一种特征扰动方法，通过系统性改变特征空间来提升迁移性评估效果。该方法包含两项操作：Spread操作增加类内差异，提升类内复杂度；Attract操作缩小类间距离，模糊类别边界。大量实验表明，该方法显著提升了迁移性评估的精确性与鲁棒性。尤其在现有LogMe方法上，应用本方法后性能提升28.84%。
原文摘要 · Abstract (English)
Leveraging a transferability estimation metric facilitates the non-trivial challenge of selecting the optimal model for the downstream task from a pool of pre-trained models. Most existing metrics primarily focus on identifying the statistical relationship between feature embeddings and the corresponding labels within the target dataset, but overlook crucial aspect of model robustness. This oversight may limit their effectiveness in accurately ranking pre-trained models. To address this limitation, we introduce a feature perturbation method that enhances the transferability estimation process by systematically altering the feature space. Our method includes a Spread operation that increases intra-class variability, adding complexity within classes, and an Attract operation that minimizes the distances between different classes, thereby blurring the class boundaries. Through extensive experimentation, we demonstrate the efficacy of our feature perturbation method in providing a more precise and robust estimation of model transferability. Notably, the existing LogMe method exhibited a significant improvement, showing a 28.84% increase in performance after applying our feature perturbation method.
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。