Piotr Bojanowski

发表论文 76 篇 · 总被引 56650 次 · h-index 38

代表论文

• DINOv2: Learning Robust Visual Features without Supervision (2023 · Trans. Mach. Learn. Res. · 被引 9587)
• DINOv3 (2025 · 被引 1205)
• Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture (2023 · Computer Vision and Pattern Recognition · 被引 1065)
• Vision Transformers Need Registers (2023 · International Conference on Learning Representations · 被引 938)
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning (2025 · arXiv.org · 被引 566)
• Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision (2022 · arXiv.org · 被引 125)