Completed
Image Output Quantization
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Single-Task Model vs. Unified Model
- 3 Single-Task Model for Vision
- 4 Image Output Quantization
- 5 Text Input for Different Tasks
- 6 Model Details
- 7 Objective
- 8 Dataset and Implementations
- 9 Pre-training Distribution
- 10 Evaluation
- 11 GRIT requires diverse skills
- 12 Results
- 13 Semantic Segmentation
- 14 Depth Estimation
- 15 Object Detection
- 16 Image Inpainting
- 17 Segmentation based image generation
- 18 Summary
- 19 Tasks Distribution
