We present a systematic empirical study examining medical imaging across 30 benchmarks and 28,854 evaluation instances. Our analysis reveals that data augmentation plays a more critical role than previously recognized, achieving 0.
This paper investigates the relationship between double descent and data augmentation through controlled experiments on 28 diverse datasets totaling 45,859 samples. We propose a novel methodology that achieves 27.
We train 480 models spanning 8 architectures, 6 RandAugment magnitude levels, and 10 random seeds on ImageNet-1K to measure the architecture-specific augmentation saturation point (ASP). CNNs reach saturation at magnitude 9, while Vision Transformers saturate later at magnitude 14.
Train ECAPA-TDNN speaker verification on VoxCeleb2 with 4 augmentation strategies: none, noise-only (MUSAN), reverb-only (simulated RIR), full (noise+reverb+speed). Test on VOiCES corpus at 5 RT60 conditions (0.