Paper Detail
Haiyang Li, Yuming Fu, Qun Song, Hongchao Liao, Jing Chen, Mounim A. EI-Yacoubi, Xin Jin
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, PuzzleMix, StarMixup) generally provide the strongest recognition performance. However, they are often poorly calibrated and vulnerable to adversarial perturbations, revealing a clear inconsistency between clean accuracy and adversarial security. We also find that severe geometric transformations frequently degrade recognition, which is potentially due to feature misalignment or spatial cropping, and that augmentation effectiveness varies across palm and finger vein datasets. These findings prove that accuracy-centric evaluation is insufficient for biometric augmentation. AGVBench provides standardized protocols to support reproducible research and guide the design of reliable, secure, and robust vein recognition systems. Our codebase is available at https://github.com/Advance-VeinTech-Innovators/AGVBench.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{li2026agvbench,
title = {AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition},
author = {Haiyang Li and Yuming Fu and Qun Song and Hongchao Liao and Jing Chen and Mounim A. EI-Yacoubi and Xin Jin},
year = {2026},
abstract = {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-},
url = {https://huggingface.co/papers/2607.02271},
keywords = {data augmentation, biometric technology, palm-vein, finger-vein, backbone architectures, CNNs, vision transformers, vein-specific recognition models, MixUp, PuzzleMix, StarMixup, adversarial perturbations, feature misalignment, spatial cropping, code available, huggingface daily},
eprint = {2607.02271},
archiveprefix = {arXiv},
}
{}