On vein-recognition benchmarks, mixup-style augmentations win on clean accuracy but hurt calibration and adversarial robustness, while simple geometric transforms usually hurt performance.
Palm vein recognition under unconstrained and weak-cooperative con- ditions.IEEE Transactions on Information Forensics and Security, 19:4601–4614, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition
On vein-recognition benchmarks, mixup-style augmentations win on clean accuracy but hurt calibration and adversarial robustness, while simple geometric transforms usually hurt performance.