Improving Image Classification Performance with Modern Data Augmentation and Vision Transformer

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Visual cognition, one of the main tasks of computer vision, has many applications, including object detection, face recognition, and self-driving automobiles. This paper discusses deep learning applications to visual cognition, including a brief history, some of its applications, and some architectures, such as Residual Networks and Residual-Inception. Visual cognition faces significant challenges when dealing with objects that have comparable forms but represent different classes. The proposed architecture in this paper incorporates Modern Data Augmentation and Vision Transformers (MDAViT) to improve accuracy. The model is trained and evaluated on the CIFAR-10 dataset, demonstrating higher accuracy against existing self-supervised methods.