MG-ViT: A Multi-Granularity Method for Compact and Efficient Vision Transformers Y u Zhang

Oct-9-2025, 09:08:48 GMT–Neural Information Processing Systems

Vision Transformer (ViT) faces obstacles in wide application due to its huge computational cost.

artificial intelligence, machine learning, transformer, (19 more...)

Neural Information Processing Systems

Oct-9-2025, 09:08:48 GMT

Conferences PDF

Country:
- Asia
  - China (0.04)
  - Middle East > Israel (0.04)
- Europe > Switzerland
  - Zürich > Zürich (0.14)

Genre:
- Research Report > New Finding (0.46)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks (0.68)
    - Vision (1.00)
  - Sensing and Signal Processing > Image Processing (1.00)