ScholarGate
アシスタント

手法を比較

選択した手法を並べて確認できます。異なる行はハイライト表示されます。

マスク化オートエンコーダ×ビジョントランスフォーマー×
分野深層学習深層学習
系統Machine learningMachine learning
提唱年20212021
提唱者Kaiming HeDosovitskiy, A. et al.
種類Neural network architectureTransformer architecture for images (self-attention over patches)
原典He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16000-16009). DOI ↗Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗
別名MAE, Vision MAEGörsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
関連45
概要Masked Autoencoders (MAE) is a self-supervised learning approach introduced by He et al. in 2021 that masks random patches of an image and trains a model to reconstruct the missing content. Adapting the masked language modeling paradigm from NLP to vision, MAE learns rich visual representations by solving a challenging reconstruction task without requiring labels.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).
ScholarGateデータセット
  1. v1
  2. 1 出典
  3. PUBLISHED
  1. v1
  2. 2 出典
  3. PUBLISHED

検索へ スライドをダウンロード

ScholarGate手法を比較: Masked Autoencoders · Vision Transformer. 2026-06-18に以下より取得 https://scholargate.app/ja/compare