Harnessing small projectors and multiple views for efficient vision pretraining

Feb-12-2026, 05:29:30 GMT–Neural Information Processing Systems

We show how this idealized loss can be reformulated to a functionally equivalent loss that is more efficient to compute.

artificial intelligence, deep learning, machine learning, (17 more...)

Neural Information Processing Systems

Feb-12-2026, 05:29:30 GMT

Conferences PDF

Country:
- Africa > Rwanda
  - Kigali > Kigali (0.04)
- Europe > United Kingdom
  - England > Cambridgeshire > Cambridge (0.04)
- North America
  - Canada
    - Ontario > Toronto (0.04)
    - Quebec > Montreal (0.14)
  - United States > California
    - Alameda County > Berkeley (0.04)

Genre:
- Research Report > New Finding (0.93)

Industry:
- Education (0.67)
- Health & Medicine (0.46)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Neural Networks > Deep Learning (0.46)
    - Statistical Learning (1.00)
  - Representation & Reasoning (1.00)
  - Vision (0.93)

Duplicate Docs Excel Report

Title
Harnessing small projectors and multiple views for efficient vision pretraining

Similar Docs Excel Report more

Title	Similarity	Source
None found