ScholarGate
Msaidizi
Machine learningDeep learning / NLP / CV

Transformer wa Maono unaojifundisha

Transformer wa Maono unaojifundisha (SSL-ViT) hutumia malengo ya mafunzo ya awali yanayojifundisha — kama vile utabiri wa kiraka kilichofichwa (MAE) au kujifundisha bila lebo (DINO) — kwa usanifu wa Transformer wa Maono, kuwezesha uwakilishi wenye nguvu wa kuona kujifunzwa kutoka kwa makusanyo makubwa ya picha zisizo na lebo kabla ya marekebisho yoyote maalum ya kazi.

Fungua katika MethodMindHivi karibuniVideoHivi karibuniDownload slides

Soma mbinu kamili

Kwa wanachama pekee

Ingia kwa akaunti ya bure ili kusoma sehemu hii.

Ingia

Method map

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

Transformer wa Maono unaojifundisha
Vision Transformer Iliyo…Transformer wa Maono wa…Self-supervised convolut…Transformer wa MaonoTransformer ya Maono Ina…Uchambuzi wa maana kwa n…Semi-supervised Instance…Mabadilishaji ya Macho Y…

Vyanzo

  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 ↗

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 3). Self-supervised Vision Transformer (SSL-ViT). ScholarGate. https://scholargate.app/sw/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 →

Imerejelewa na

Transformer ya Maono InayoelewekaSelf-supervised convolutional neural networkUchambuzi wa maana kwa njia ya kujitegemeaSemi-supervised Instance SegmentationMabadilishaji ya Macho Yaliyosaidiwa kwa Nusu

Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →

ScholarGate — Self-supervised Vision Transformer (Self-supervised Vision Transformer (SSL-ViT)). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/self-supervised-vision-transformer · Seti ya data: https://doi.org/10.5281/zenodo.20539026