动态生成特征提取器，实现已知与未知人脸的统一识别
FaceGCD: Generalized Face Discovery via Dynamic Prefix Generation
- 用轻量级前缀动态构建身份专属特征提取器
- 在开放世界人脸任务上超越现有方法，显著提升识别效果
- 适合需要处理大量细粒度身份识别的AI系统开发者
人脸识别系统需同时识别已知和未知人脸，这是迈向通用人工智能的关键。本文提出广义人脸发现（GFD）新任务，将传统识别与广义类别发现（GCD）统一。该任务要求识别已知标签与未标记身份，并发现全新未见身份。由于人脸身份数量多、差异细微，现有GCD方法效果不佳。为此，我们提出FaceGCD，通过超网络实时生成轻量级、逐层的前缀，动态构建实例相关特征提取器。该设计无需高容量静态模型即可捕捉细微身份特征。大量实验表明，FaceGCD显著优于现有GCD方法及强基准模型ArcFace，达到当前最佳性能，推动开放世界人脸识别发展。
原文摘要 · Abstract (English)
Recognizing and differentiating among both familiar and unfamiliar faces is a critical capability for face recognition systems and a key step toward artificial general intelligence (AGI). Motivated by this ability, this paper introduces generalized face discovery (GFD), a novel open-world face recognition task that unifies traditional face identification with generalized category discovery (GCD). GFD requires recognizing both labeled and unlabeled known identities (IDs) while simultaneously discovering new, previously unseen IDs. Unlike typical GCD settings, GFD poses unique challenges due to the high cardinality and fine-grained nature of face IDs, rendering existing GCD approaches ineffective. To tackle this problem, we propose FaceGCD, a method that dynamically constructs instance-specific feature extractors using lightweight, layer-wise prefixes. These prefixes are generated on the fly by a HyperNetwork, which adaptively outputs a set of prefix generators conditioned on each input image. This dynamic design enables FaceGCD to capture subtle identity-specific cues without relying on high-capacity static models. Extensive experiments demonstrate that FaceGCD significantly outperforms existing GCD methods and a strong face recognition baseline, ArcFace, achieving state-of-the-art results on the GFD task and advancing toward open-world face recognition.
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。