2024/11/01 by David A. Danhofer, Danhofer, David A.
Computer Science · Neuroscience · #Artificial Intelligence (cs.AI) #Brain Tumor Detection and Classification #C.4 #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #I.2.10 #I.2.6 #I.4.m #I.5.4 #I.5.5 #Machine Learning (cs.LG) #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Performance (cs.PF) #Stochastic Gradient Optimization Techniques
paper · pdf · doi:10.48550/arxiv.2411.00288
openalex publication_date 2024/11/01 · openalex created_date 2024/11/14 · openalex updated_date 2026/07/28
The crucial role of convolutional models, both as standalone vision models and backbones in foundation models, necessitates effective acceleration techniques. This paper proposes a novel method to learn semi-structured sparsity patterns for convolution kernels in the form of maskings enabling the utilization of readily available hardware accelerations. The approach accelerates convolutional models more than two-fold during inference without decreasing model performance. At the same time, the original model weights and structure remain unchanged keeping the model thus easily updatable. Beyond the immediate practical use, the effect of maskings on prediction is easily quantifiable. Therefore, guarantees on model predictions under maskings are derived showing stability bounds for learned maskings even after updating the original underlying model.