发表机构
Linköping University（林雪平大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究对比分析深度学习中无标签表示质量度量，按构造分类并建立关联，经合成实验、260种视觉模型及6个数据集验证，发现本征维度（ID）最可靠，且所有度量可靠性受架构类别和训练目标调节，为相关度量的理解与应用提供了清晰依据。
AI 中文摘要
我们开展深度学习中用于评估深度神经网络表示质量的无标签度量的对比研究，以理解其在多种配置下的可靠性。我们根据现有无标签度量的构造将其分为三类，并分析性地建立同一类内度量之间的联系。随后，我们通过受控合成实验表征谱度量的敏感性。最后，我们针对下游任务准确率，在涵盖通用对象分类、细粒度对象分类、场景识别和地理空间任务的6个数据集上，对260种不同视觉模型评估所有无标签度量，并按架构类别和训练目标分层呈现结果。我们发现本研究考虑的度量中，本征维度（ID）是最可靠的预测因子，但包括ID在内的所有度量的可靠性均受架构类别和训练目标的调节。我们的研究结果更清晰地阐明了无标签表示质量度量所衡量的内容、其可靠的场景以及实践中的解释方式。
英文摘要
We present a comparative study of label-free metrics for assessing the quality of representations in deep neural networks to understand their reliability under a wide variety of configurations. We group existing label-free metrics into three families based on their construction and analytically establish connections between metrics within the same family. We then characterise the sensitivity of spectral metrics through controlled synthetic experiments. Finally, all label-free metrics are evaluated against downstream task accuracy across a diverse set of 260 vision models on six datasets spanning generic object classification, fine-grained object classification, scene recognition and geospatial task, stratifying results by architecture class and training objective. We find that intrinsic dimensionality (ID) is the most reliable predictor among the metrics considered. However, the reliability of all metrics, including ID, is moderated by architecture class and training objective. Our results provide a clearer understanding of what label-free representation quality metrics measure, when they are reliable, and how to interpret them in practice.
CommentsPublished in Transactions on Machine Learning Research (TMLR). OpenReview: https://openreview.net/forum?id=yknkAksqr1
Journal refTransactions on Machine Learning Research (2026), ISSN 2835-8856
