CIFAR-100

Discover how LayerMix, an innovative data augmentation technique using structured fractal mixing, enhances deep learning model robustness against corruptions, adversarial attacks, and distribution shifts. Learn about its methodology, benchmarks, and results.

LayerMix: A Fractal-Based Data Augmentation Strategy for More Robust Deep Learning Models

Deep Learning (DL) has revolutionized computer vision, enabling machines to identify objects, segment images, and drive cars with astonishing accuracy. Yet, a critical Achilles’ heel remains: these models often fail dramatically when faced with data that deviates even slightly from…

LayerMix: A Fractal-Based Data Augmentation Strategy for More Robust Deep Learning Models Read More »

Inside LSSKD, a Self Supervised Distillation Framework That Trains Small Models Without a Teacher

Inside LSSKD, a Self Supervised Distillation Framework That Trains Small Models Without a Teacher

Every knowledge distillation paper eventually asks the same question a cash strapped engineering team asks first. Do we really need a giant teacher model sitting around just so a small model can learn from it, or can the small model…

Inside LSSKD, a Self Supervised Distillation Framework That Trains Small Models Without a Teacher Read More »