提出归一化池化模板生成法，提升多域人脸识别性能。
Template-based Multi-Domain Face Recognition
- 用归一化池化生成更鲁棒的人脸模板
- 在IJB-MDF数据集上超越平均池化，跨域表现更好
- 适合低数据量目标域的实用人脸识别场景
尽管深度神经网络在可见光域的人脸检测与识别任务中表现优异，但在更具挑战性的非可见光域（如SWIR、远距离监控、体佩戴设备等）上性能仍不足。针对目标域缺乏训练数据导致领域自适应与领域泛化方法难以应用的问题，本文聚焦于单源（可见光）到多目标（SWIR、远距/远程、监控、体佩戴）的人脸识别任务。实验表明，随着目标域复杂度增加，模板生成算法的质量变得至关重要。为此，提出一种名为归一化池化（Norm Pooling）及其变体稀疏池化（Sparse Pooling）的模板生成方法。在IARPA JANUS基准多域人脸数据集（IJB-MDF）上，该方法在不同网络架构和域间均优于平均池化，显著提升跨域识别效果。
原文摘要 · Abstract (English)
Despite the remarkable performance of deep neural networks for face detection and recognition tasks in the visible spectrum, their performance on more challenging non-visible domains is comparatively still lacking. While significant research has been done in the fields of domain adaptation and domain generalization, in this paper we tackle scenarios in which these methods have limited applicability owing to the lack of training data from target domains. We focus on the problem of single-source (visible) and multi-target (SWIR, long-range/remote, surveillance, and body-worn) face recognition task. We show through experiments that a good template generation algorithm becomes crucial as the complexity of the target domain increases. In this context, we introduce a template generation algorithm called Norm Pooling (and a variant known as Sparse Pooling) and show that it outperforms average pooling across different domains and networks, on the IARPA JANUS Benchmark Multi-domain Face (IJB-MDF) dataset.
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。