GA-SAM: Gradient-strength based adaptive sharpness-aware minimization for improved generalization
Recently, Sharpness-Aware Minimization (SAM) algorithm has shown state-of-the-art
generalization abilities in vision tasks. It demonstrates that flat minima tend to imply better …
generalization abilities in vision tasks. It demonstrates that flat minima tend to imply better …
[PDF][PDF] DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion: Supplementary Materials
A Douillard, A Ramé, G Couairon, M Cord - openaccess.thecvf.com
Datasets We use three datasets: CIFAR100 [15], ImageNet100, and ImageNet1000 [4].
CIFAR100 is made of 50,000 train RGB images and 10,000 test RGB images of size 32× 32 …
CIFAR100 is made of 50,000 train RGB images and 10,000 test RGB images of size 32× 32 …