ScholarGate
Pembantu

Bandingkan kaedah

Semak kaedah pilihan anda secara bersebelahan; baris yang berbeza akan diserlahkan.

Transformer Visi×Mesin Vektor Sokongan (Klasifikasi)×
BidangPembelajaran MendalamPembelajaran Mesin
KeluargaMachine learningMachine learning
Tahun asal20211995
PengasasDosovitskiy, A. et al.Cortes, C. & Vapnik, V.
JenisTransformer architecture for images (self-attention over patches)Maximum-margin classifier (kernel method)
Sumber perintisDosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297. DOI ↗
AliasGörsel Transformer (ViT), görsel transformer, ViT, patch transformer for imagesDestek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
Berkaitan55
RingkasanThe 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).The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data.
ScholarGateSet data
  1. v1
  2. 2 Sumber
  3. PUBLISHED
  1. v1
  2. 1 Sumber
  3. PUBLISHED

Pergi ke carian Muat turun slaid

ScholarGateBandingkan kaedah: Vision Transformer · Support Vector Machine. Dicapai 2026-06-15 daripada https://scholargate.app/ms/compare