Learning Vision from Models Rivals Learning Vision from Data

arxiv:2312.17742

Original source · Paper JSON

Data, training, optimization · 2023-12-28

Cites (5) · Cited by (0)

Complete cleaned Markdown · Source Markdown including bibliography

Read in parts

1. Part 1
2. Part 2
3. Part 3

Contents

• Learning Vision from Models Rivals Learning Vision from Data
• Abstract
• 1 Introduction
• 2 Related Works
• 3 Approach
• 3.1 Synthesizing captions
• 3.2 Synthesizing Images
• 3.3 Representation Learning
• 3.4 Implementation
• 4 Experiment
• 4.1 Study different components
• 4.2 Scaling up
• 4.3 Further analysis
• 5 Discussions and Conclusion
• Appendix A Concept Sampling
• Appendix B Implementation Details
• B.1 Pre-training
• B.2 ImageNet linear probing
• B.3 End-to-End ImageNet fine-tuning
• B.4 Semantic segmentation on ADE20k
• B.5 Fine-grained linear classification
• Appendix C In-context Learning Examples
• Instructions for reporting errors