Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models
Researchers have developed a new training protocol called RBDC to make training large vision models more resource-efficient. This method involves recursively coupling independently trained, narrower models in a parameter-free block-diagonal manner. Evaluations on ImageNet using Vision Transformers and ResNets demonstrated a 30% FLOPs reduction with comparable accuracy and improved performance at the same training FLOPs compared to existing growth methods. The RBDC-trained models also showed enhanced utility as backbones for downstream tasks like object detection and instance segmentation. AI
IMPACT Reduces computational costs for training large vision models, potentially accelerating research and deployment.