ScholarGate
Asisten
Machine learningDeep learning / NLP / CV

Vision Transformer Pengawasan Mandiri

Vision Transformer Pengawasan Mandiri (SSL-ViT) menerapkan tujuan pra-pelatihan pengawasan mandiri — seperti prediksi tambalan bertopeng (MAE) atau distilasi mandiri tanpa label (DINO) — pada arsitektur Vision Transformer, memungkinkan representasi visual yang kuat dipelajari dari korpus gambar besar tak berlabel sebelum penyetelan halus spesifik tugas apa pun.

Buka di MethodMindSegeraVideoSegeraDownload slides

Baca metode selengkapnya

Khusus anggota

Masuk dengan akun gratis untuk membaca bagian ini.

Masuk

Method map

The neighbourhood of related methods — select a node to explore.

Sumber

  1. Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging Properties in Self-Supervised Vision Transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 9650–9660. link
  2. He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022). Masked Autoencoders Are Scalable Vision Learners. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 16000–16009. link

Cara menyitasi halaman ini

ScholarGate. (2026, June 3). Self-supervised Vision Transformer (SSL-ViT). ScholarGate. https://scholargate.app/id/deep-learning/self-supervised-vision-transformer

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Dirujuk oleh

ScholarGateSelf-supervised Vision Transformer (Self-supervised Vision Transformer (SSL-ViT)). Diakses 2026-06-15 dari https://scholargate.app/id/deep-learning/self-supervised-vision-transformer · Set data: https://doi.org/10.5281/zenodo.20539026