Self-supervised Vision Transformer
Self-supervised Vision Transformer (SSL-ViT) primenjuje ciljeve samonadgledanog pred-treninga — kao što su predikcija maskiranih delova (MAE) ili samoučenje bez oznaka (DINO) — na arhitekturu Vision Transformer, omogućavajući učenje moćnih vizuelnih reprezentacija iz velikih korpusa neoznačenih slika pre bilo kakvog finog podešavanja specifičnog za zadatak.
Pročitajte celu metodu
Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.
Method map
The neighbourhood of related methods — select a node to explore.
Izvori
- 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 ↗
- 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 ↗
Kako citirati ovu stranicu
ScholarGate. (2026, June 3). Self-supervised Vision Transformer (SSL-ViT). ScholarGate. https://scholargate.app/sr/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.
- Fine-Tuned Vision TransformerDuboko učenje↔ compare
- Multimodal Vision TransformerDuboko učenje↔ compare
- Samonadzirana konvoluciona neuronska mrežaDuboko učenje↔ compare
- Vision TransformerDuboko učenje↔ compare
Citirana u
Uočili ste grešku na ovoj stranici? Prijavite je ili predložite ispravku →