ScholarGate
Avustaja

Vertaile menetelmiä

Tarkastele valitsemiasi menetelmiä rinnakkain; eroavat rivit korostetaan.

Itseohjautuva Vision Transformer×Vision Transformer×
TieteenalaSyväoppiminenSyväoppiminen
MenetelmäperheMachine learningMachine learning
Syntyvuosi2021–20222021
KehittäjäCaron et al. (DINO); He et al. (MAE)Dosovitskiy, A. et al.
TyyppiSelf-supervised pre-training for vision transformersTransformer architecture for images (self-attention over patches)
AlkuperäislähdeCaron, 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 ↗Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗
RinnakkaisnimetSSL-ViT, self-supervised ViT, unsupervised ViT pre-training, vision transformer self-supervised pre-trainingGörsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Liittyvät45
TiivistelmäSelf-supervised Vision Transformer (SSL-ViT) applies self-supervised pre-training objectives — such as masked patch prediction (MAE) or self-distillation with no labels (DINO) — to the Vision Transformer architecture, enabling powerful visual representations to be learned from large unlabeled image corpora before any task-specific fine-tuning.The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs).
ScholarGateAineisto
  1. v1
  2. 2 Lähteet
  3. PUBLISHED
  1. v1
  2. 2 Lähteet
  3. PUBLISHED

Siirry hakuun Lataa diat

ScholarGateVertaile menetelmiä: Self-supervised Vision Transformer · Vision Transformer. Haettu 2026-06-17 osoitteesta https://scholargate.app/fi/compare