无需标注数据，自动确定人脸识别等任务的相似度阈值。
How Far is Too Far? Defining the Distance Threshold for Verification Siamese Networks
- 假设距离分布为双峰，通过峰谷点定位最佳阈值
- 在四个数据集上平均准确率达94%，媲美有监督方法
- 适合部署后实时更新阈值，无需人工标注
Siamese验证网络广泛用于人脸、车辆或签名等项目比较。网络训练目标是使相似对象在嵌入空间中更接近，不相似对象则更远。当两个对象嵌入距离低于预设阈值时，判定为同类别。然而，阈值设定非易事，通常需依赖标注数据。本文假设验证网络产生的距离分布近似双峰函数，提出一种无监督方法：通过识别两峰之间的最小点来确定阈值。该方法无需标注样本，可直接在部署环境更新阈值，避免人工标注成本。我们在MNIST、CIFAR-10、LFW和PKLot四个数据集上评估，结果表明该方法平均验证准确率达94%，与等错误率（Equal Error Rate）方法相当。
原文摘要 · Abstract (English)
Siamese verification networks are widely used to compare items such as faces, cars, or signatures. In these scenarios, the network is trained to learn an embedding space in which similar objects are mapped closer together, while dissimilar objects are mapped further apart. Two objects are considered to belong to the same class (e.g., the same person in two different images) when the distance between their embeddings falls below a predefined threshold. Defining this threshold, however, is a non-trivial task and typically requires labeled data. In this work, we assume that the distribution of distances produced by a siamese verification network can be approximated by a bimodal function. Based on this assumption, we propose an unsupervised method to determine the verification threshold by identifying the minimum point between the two modes. The proposed approach does not require annotated samples, enabling the verification threshold to be updated directly in the deployment environment without the cost of manual labeling. We evaluate our method on four datasets: MNIST, CIFAR-10, LFW, and PKLot. The results indicate that the proposed approach achieves an average verification accuracy of 94%, comparable to the Equal Error Rate method, while eliminating the need for labeled data.
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。