Completed
- Model architecture: many parts for many tasks
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
BLIP- Bootstrapping Language-Image Pre-Training for Unified Vision-Language Understanding and Generation
Automatically move to the next video in the Classroom when playback concludes
- 1 - Intro
- 2 - Sponsor: Zeta Alpha
- 3 - Paper Overview
- 4 - Vision-Language Pre-Training
- 5 - Contributions of the paper
- 6 - Model architecture: many parts for many tasks
- 7 - How data flows in the model
- 8 - Parameter sharing between the modules
- 9 - Captioning & Filtering bootstrapping
- 10 - Fine-tuning the model for downstream tasks
