A data efficient transformer based on Swin Transformer

• Published in: The Visual computer Vol. 40; no. 4; pp. 2589 - 2598
• Main Authors: Yao, Dazhi, Shao, Yunxue
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2024; Springer Nature B.V
• Subjects: Accuracy; Artificial Intelligence; Classification; Computer Graphics; Computer Science; Computing costs; Datasets; Design; Image Processing and Computer Vision; Massive data points; Modules; Neural networks; Original Article; Computer vision; Transformer; Data efficient; Classification

Almost all Vision Transformer-based models need to pre-train on the massive datasets and costly computation. Suppose researchers do not have enough data to train a Vision Transformer-based model or do not have powerful GPUs to implement computation for millions of labeled data. In that case, Vision...