Paper Review: ConvNext or Convnets for 2020s

Recently there was a huge shift in the field of computer vision and it was due to the application of transformers (an idea developed for NLP) to images and videos. Vision Transformers or ViT became hugely famous and it had beaten almost every other ConvNet based approach, followed by more advancements with transformers like DieT and Swin Transformers. But in 2022, Facebook’s research team heavily investigated the ConvNets and by removing all the possible bottlenecks, they were able to surpass all other previously trained networks. Before we jump into the detailed discussion let…