Tag: image classification
-
EfficientNetV2 vs ResNet: 11x Faster Training Explained
EfficientNetV2 trains 11x faster than ResNet through progressive learning, Fused-MBConv blocks, and adaptive regularization strategies.
-
ViT Review: 16×16 Patches That Replaced Convolutions
ViT-B/16 hits 77.9% top-1 accuracy on ImageNet with 16x16 patches and no convolutions. We review the architecture, training tricks, and where it breaks.
-
ViT vs DeiT Review: Pure Attention Meets Distillation
ViT vs DeiT: how distillation and data augmentation let DeiT match ViT accuracy without 300M pretraining images. Training logs and ablation results included.