Exploring the synergies of hybrid convolutional neural network and Vision Transformer architectures for computer vision: A survey

The hybrid of Convolutional Neural Network (CNN) and Vision Transformer (ViT) architecture has emerged as a groundbreaking approach, pushing the boundaries of Computer Vision (CV), significantly advancing CV tasks such as image classification, object detection, and segmentation. This comprehensive review provides a thorough examination of the literature on state-of-the-art hybrid CNN-ViT architectures, exploring the synergies between these two approaches. The main content of this survey includes: (1) a background on the vanilla CNN and ViT, (2) systematic review of various taxonomic hybrid designs to explore the synergy achieved through merging CNN and ViT models, (3) comparative analysis, task-specific synergy and real-world application among various hybrid architectures, (4) challenges and future directions for hybrid models, (5) lastly, the survey concludes with a summary of key findings and recommendations. Through this exploration, the survey aims to serve as a guiding resource, enhancing understanding of the dynamics between CNN and ViT and their impact on future developments in CV.