发表机构
Stanford University（斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文设计TLDChoiceNet模型，通过预测微调后测试集准确率选择最优迁移学习数据集，提出分布距离与平均类别相关性指标，相关指标可有效预测迁移学习效果。
AI 中文摘要
迁移学习在训练数据有限的场景中尤为有用，在图像分类领域，人们通常会在ImageNet、CIFAR-100或COCO等大型数据集上进行迁移学习。从定性角度看，迁移学习数据集似乎应比微调数据集拥有更多类别，且每个类别包含更多样本；然而，目前并不存在选择最佳迁移学习数据集的定量方法。在本文中，我们设计了TLDChoiceNet这一模型，该模型可在给定微调数据集的情况下，通过预测微调后的测试集准确率来选择最佳迁移学习数据集。简单版1在测试数据集上的均方误差（MSE）为0.154，而利用ImageNet预训练ResNet50 v2嵌入及类别信息的版本2，其MSE降至0.031，降幅达5倍。我们进一步设计了两个指标，可实现选择最优迁移学习数据集的无监督方法：分布距离（DD），其与微调准确率的线性回归R²为0.89；平均类别相关性（ACC），其将R²提升至0.97。我们的结果表明，数据集的低级统计量可解释迁移学习效果，且使用预训练ImageNet可在潜在特征空间中将不同类别嵌入得更分散。
英文摘要
Transfer learning is particularly useful in settings with limited training data, and within image classification it is common to transfer learn upon massive datasets like ImageNet , CIFAR-100, or COCO . Qualitatively, it seems a transfer learning dataset should have both more classes and more examples per class than the fine tuning dataset; however, a quantitative method to choose the best transfer learning dataset does not currently exist. In this paper, we design TLDChoiceNet, a model to choose the best transfer learning dataset given a fine tuning dataset by predicting the test-set accuracy after fine-tuning. A simple version 1 achieves 0.154 MSE on the test dataset, while a version 2 leveraging an ImageNet pre-trained ResNet50 v2 embedding with per-class information attains a 5X lower MSE of 0.031. We further design two metrics that enable an unsupervised method of choosing an optimal transfer learning dataset: distribution distance (DD), which linearly regresses against fine-tune accuracy with an R2 of 0.89, and average class correlation (ACC), which improves the R2 to 0.97. Our results underscore that a dataset's low-level statistics can explain the transfer learning effect, and that using a pre-trained ImageNet can embed different classes further apart in latent feature space.
