Search Results for author:
Found 4 papers, 0 papers with code
SkipViT: Speeding Up Vision Transformers with a Token-Level Skip Connection
Our method does not add any parameters to the ViT model and aims to find the best trade-off between training throughput and achieving a 0% loss in the Top-1 accuracy of the final model.
SwiftLearn: A Data-Efficient Training Method of Deep Learning Models using Importance Sampling
In this paper, we present SwiftLearn, a data-efficient approach to accelerate training of deep learning models using a subset of data samples selected during the warm-up stages of training.
GQKVA: Efficient Pre-training of Transformers by Grouping Queries, Keys, and Values
We tested our method on ViT, which achieved an approximate 0. 3% increase in accuracy while reducing the model size by about 4% in the task of image classification.
Multi-Task Learning For Reduced Popularity Bias In Multi-Territory Video Recommendations
Our proposed framework is designed to enrich training examples with active users representation through upsampling, and capable of learning geographic-based user embeddings by leveraging MTL.
