운동하는 공대생

논문 - https://arxiv.org/abs/2211.05778 InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state. This work presents a new large-scale CNN-based foundation model, termed arxiv.org 1. In..