AGVBench benchmarks 30 augmentation strategies for vein recognition and finds mixing methods improve accuracy but harm calibration and adversarial robustness.
Autoaugment: Learning augmentation strategies from data
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
StableTTA improves ImageNet-1K accuracy across 71 vision models by stabilizing logit aggregation under coherent-batch inference and enabling efficient single-forward-pass adaptation.
citing papers explorer
-
AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition
AGVBench benchmarks 30 augmentation strategies for vein recognition and finds mixing methods improve accuracy but harm calibration and adversarial robustness.
-
StableTTA: Improving Vision Model Performance by Training-free Test-Time Adaptation Methods
StableTTA improves ImageNet-1K accuracy across 71 vision models by stabilizing logit aggregation under coherent-batch inference and enabling efficient single-forward-pass adaptation.