判别跨度作为通过分类器重构预测合成数据效用的指标
Discriminative Span as a Predictor of Synthetic Data Utility via Classifier Reconstruction
AI总结：
本文提出一种几何驱动的指标，通过预训练模型的嵌入空间评估合成数据效用，无需模型训练，通过测量线性分类器权重向量在变化子空间中的投影误差，判断合成数据对下游分类性能的影响。
摘要：
在许多现实世界计算机视觉应用中，如医学影像和工业检测，二分类任务常面临正样本严重缺乏的问题。广泛采用的解决方案是通过图像到图像转换生成合成正样本。然而，一个根本性挑战是：如何可靠地评估此类合成数据是否能提升下游模型性能？本文提出一种几何驱动的指标，该指标可预测合成数据的效用，而无需模型训练。我们的方法在预训练基础模型的嵌入空间中操作，并通过样本之间的差异向量表示数据集。我们通过测量线性分类器权重向量在这些变化子空间中的投影误差，评估其是否可被表示在该子空间内。直观上，如果合成数据诱导的变化捕捉了任务相关方向，其张量可近似分类器，导致投影误差低。反之，质量差的合成数据无法张量这些方向，导致误差高。在多个数据集和架构上，我们证明该指标与混合真实负样本和合成正样本训练的CNN下游分类性能有强相关性。这些发现表明，所提指标是评估数据稀缺设置中合成数据质量的实用且信息丰富的工具。
英文摘要：
In many real-world computer vision applications, including medical imaging and industrial inspection, binary classification tasks are characterized by a severe scarcity of positive samples. A widely adopted solution is to generate synthetic positive data using image-to-image transformations applied to negative samples. However, a fundamental challenge remains: how can we reliably assess whether such synthetic data will improve downstream model performance? In this work, we propose a geometry-driven metric that predicts the utility of synthetic data without requiring model training. Our approach operates in the embedding space of a pre-trained foundation model and represents the dataset through difference vectors between samples. We evaluate whether the weight vector of a linear classifier can be expressed within the subspace spanned by these variations by measuring the relative projection error. Intuitively, if the variations induced by synthetic data capture task-relevant directions, their span can approximate the classifier, resulting in low projection error. Conversely, poor synthetic data fails to span these directions, leading to higher error. Across multiple datasets and architectures, we show that this metric exhibits strong correlation with downstream classification performance of CNNs trained on mixtures of real negative and synthetic positive data. These findings suggest that the proposed metric serves as a practical and informative tool for evaluating synthetic data quality in data-scarce settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
