AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition

  • 类型：arxiv
  • 标识：2607.02271
  • 链接：https://arxiv.org/abs/2607.02271
  • 主分类：evaluation
  • 形态：benchmark
  • 被引：0
  • 被引来源：Semantic Scholar + OpenAlex
  • S2被引：0
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：Vein recognition is a secure biometric technology often constrained by limited annotated data and imaging variations. While data augmentation mitigates this, strategies designed for natural images may disrupt the fine-grained topology and textures essential for identity discrimination. We present AGVBench, which evaluates 30 representative augmentation strategies on five public palm- and finger-vein datasets with seven backbone architectures, covering classic CNNs, vision transformers, and vein-specific recognition models. Our results show that multi-image mixing methods (e.g., MixUp, PuzzleMi
  • OpenAlex ID：W7167269903
  • OpenAlex DOI：10.48550/arxiv.2607.02271
  • DOI：10.48550/arxiv.2607.02271
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2607.02271
  • OpenAlex更新：2026-07-19
  • 待LLM分类：否
  • 标题中文：AGVBench：面向可靠性的静脉识别数据增强基准
  • TLDR中文：静脉识别是一种安全生物特征技术，常受限于标注数据稀缺与成像差异；而面向自然图像设计的增强策略可能破坏其关键的细粒度拓扑与纹理。本文提出 AGVBench，在 5 个公开掌/指静脉数据集、7 种骨干网络（含经典 CNN、视觉 Transformer 及静脉专用模型）上评测 30 种代表性增强策略。结果显示，多图混合类方法（如 MixUp、PuzzleMix……
  • 来源文件：
  • /inbox/tom/_candidates/2026-07-06-agent-memory-tool-use-candidates.json
  • /inbox/tom/_candidates/2026-07-05-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-07-04-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-07-03-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]