LOTUS: Improving Transformer Efficiency with Sparsity Pruning and Data Lottery Tickets
This work addresses efficiency challenges in training vision transformers for computer vision applications, representing an incremental improvement by combining existing techniques.
The paper tackled the problem of high computational demands in vision transformers by introducing LOTUS, a method that uses data lottery ticket selection and sparsity pruning to accelerate training while maintaining accuracy, achieving rapid convergence and high accuracy with significantly reduced computational requirements.
Vision transformers have revolutionized computer vision, but their computational demands present challenges for training and deployment. This paper introduces LOTUS (LOttery Transformers with Ultra Sparsity), a novel method that leverages data lottery ticket selection and sparsity pruning to accelerate vision transformer training while maintaining accuracy. Our approach focuses on identifying and utilizing the most informative data subsets and eliminating redundant model parameters to optimize the training process. Through extensive experiments, we demonstrate the effectiveness of LOTUS in achieving rapid convergence and high accuracy with significantly reduced computational requirements. This work highlights the potential of combining data selection and sparsity techniques for efficient vision transformer training, opening doors for further research and development in this area.