用局部感受野分解人脸相似度，让模型决策更透明。
Restricted Receptive Fields for Face Verification
- 将人脸相似性拆解为小块区域的贡献之和，实现可解释性设计
- 28x28小块即可达到媲美主流方法的验证性能
- 无需事后解释，适合需要可解释性的安防与身份认证场景
理解深度神经网络的决策机制对分析其行为、诊断失败案例至关重要。在计算机视觉中，常用事后方法为像素分配重要性以提升可解释性。尽管广泛应用，这些方法因缺乏可靠评估指标，其与模型真实推理过程的保真度存疑。这促使我们采用另一种思路：设计内在可解释的模型。本文提出一种人脸相似性度量方法，将全局相似性分解为受限感受野的贡献。该方法将两张人脸图像的相似性定义为多个局部块相似度得分的总和，提供无需依赖事后分析的局部可加解释。实验表明，即使使用112x112人脸图像中的28x28小块，该方法仍能实现具有竞争力的验证性能；当采用56x56块时，性能超越现有最先进方法。
原文摘要 · Abstract (English)
Understanding how deep neural networks make decisions is crucial for analyzing their behavior and diagnosing failure cases. In computer vision, a common approach to improve interpretability is to assign importance to individual pixels using post-hoc methods. Although they are widely used to explain black-box models, their fidelity to the model's actual reasoning is uncertain due to the lack of reliable evaluation metrics. This limitation motivates an alternative approach, which is to design models whose decision processes are inherently interpretable. To this end, we propose a face similarity metric that breaks down global similarity into contributions from restricted receptive fields. Our method defines the similarity between two face images as the sum of patch-level similarity scores, providing a locally additive explanation without relying on post-hoc analysis. We show that the proposed approach achieves competitive verification performance even with patches as small as 28x28 within 112x112 face images, and surpasses state-of-the-art methods when using 56x56 patches.
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。