Vision Transformer

Named by 3 kept items in this workspace.

1 items name it under classification.key entities, 1 under classification.technologies and 1 under frameworks and tools.

Search every workspace for Vision Transformer. It matches the name as written, so it can find other things that share it.

The items that name it 3

Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibration
paperas classification.technologies2026-10-06
Image Classifiers are Efficient Self-Supervised Video Representation Learners
paperas frameworks and tools2026-09-30It is written here as Vision Transformer (ViT).
Shared encoder architecture repurposed from image classification to align embeddings of two masked video views via a masked Siamese loss, without a decoder.
Copy the Same, Distill the Difference: Initializing Linear Vision Transformers
paperas classification.key entities2026-09-28

All technologies in this workspace.