通过奇异值分解预测CNN对图像的泛化能力，识别模型易出错样本。
A Priori Generalizability Estimate for a CNN
- 用全网络奇异值分解提取左右奇异向量，构建诊断工具。
- 右投影比在无标签数据下与分割性能相关，可预估模型表现。
- 能发现类别不平衡问题，适合评估模型鲁棒性
我们提出了对整个卷积神经网络进行截断奇异值分解的方法。结果表明，计算得到的左、右奇异向量有助于识别模型可能表现不佳的图像。为此，定义了两个指标：右投影比（Right Projection Ratio）和左投影比（Left Projection Ratio），分别评估图像（标签）在右（左）奇异向量上的投影保真度。实验发现，这两个比率均能检测图像分类任务中的类别不平衡现象。此外，仅需无标签数据的右投影比，与模型在图像分割任务中的表现具有相关性，表明其可作为估计模型对特定样本泛化能力的有效指标。
原文摘要 · Abstract (English)
We formulate truncated singular value decompositions of entire convolutional neural networks. We demonstrate the computed left and right singular vectors are useful in identifying which images the convolutional neural network is likely to perform poorly on. To create this diagnostic tool, we define two metrics: the Right Projection Ratio and the Left Projection Ratio. The Right (Left) Projection Ratio evaluates the fidelity of the projection of an image (label) onto the computed right (left) singular vectors. We observe that both ratios are able to identify the presence of class imbalance for an image classification problem. Additionally, the Right Projection Ratio, which only requires unlabeled data, is found to be correlated to the model's performance when applied to image segmentation. This suggests the Right Projection Ratio could be a useful metric to estimate how likely the model is to perform well on a sample.
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。