PyTorch implementation and pretrained models for DINO. For details, see Emerging Properties in Self-Supervised Vision Transformers. Run DINO with ViT-small network on a single node with 8 GPUs for 100 ...
05/22/2025 - We developed a lightweight registration package featuring several top-performing models, along with tutorials on how to deploy them on some public datasets and benchmarks. See details ...
Abstract: This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback