본문으로 건너뛰기

Juhyeon's Blog

태그: vision-transformer

5건의 항목

  • 2026년 6월 04일

    An Image is Worth 16x16 Words - Transformers for Image Recognition at Scale

    • paper
    • vision-transformer
    • self-attention
    • image-classification
    • large-scale-pretraining
    • inductive-bias
  • 2026년 6월 04일

    Emerging Properties in Self-Supervised Vision Transformers

    • paper
    • self-supervised-learning
    • self-distillation
    • vision-transformer
    • momentum-encoder
    • emergent-properties
    • representation-learning
    • image-recognition
  • 2026년 6월 04일

    Learning and Leveraging World Models in Visual Representation Learning

    • paper
    • self-supervised-learning
    • world-model
    • JEPA
    • vision-transformer
    • representation-learning
    • equivariance
  • 2026년 6월 04일

    Masked Autoencoders Are Scalable Vision Learners

    • paper
    • self-supervised-learning
    • masked-autoencoder
    • masked-image-modeling
    • vision-transformer
    • representation-learning
  • 2026년 6월 04일

    Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

    • paper
    • self-supervised-learning
    • jepa
    • representation-learning
    • vision-transformer
    • world-model
    • masked-image-modeling

키보드 단축키

/ 또는 Ctrl+K검색
?단축키 도움말
Esc모달 닫기

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Blog