DIP: Unsupervised Dense In-Context Post-training of Visual Representations

@misc{gidaris2025dipunsuperviseddense,
      title={DIP: Unsupervised Dense In-Context Post-training of Visual Representations},
      author={Spyros Gidaris and Andrei Bursuc and Antonin Vobecky and Nicolas Thome and Sophia Sirko-Galouchenko},
      year={2025},
      eprint={2506.18463},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2506.18463},
}