Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition

Aug-14-2025, 20:52:42 GMT–Neural Information Processing Systems

They split every 2D image into a fixed number of patches, each of which is treated as a token.

machine learning, natural language, pattern recognition, (15 more...)

Neural Information Processing Systems

Aug-14-2025, 20:52:42 GMT

Conferences PDF

Country:
- Asia > China
  - Beijing > Beijing (0.04)
- North America > United States
  - Minnesota > Hennepin County > Minneapolis (0.14)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning
      - Neural Networks > Deep Learning (0.68)
      - Pattern Recognition > Image Matching (0.41)
    - Natural Language (1.00)
    - Vision (1.00)
  - Sensing and Signal Processing > Image Processing (1.00)

Duplicate Docs Excel Report

Title
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition

Similar Docs Excel Report more

Title	Similarity	Source
None found