Completed
Architecture - DAMSM loss
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Problem: Text-to-image
- 3 Related work
- 4 Architecture - Motivation
- 5 Architecture - Text Encoder
- 6 Architecture - Conditioning Augmentation
- 7 Architecture - Generator F.
- 8 Architecture - Attention network Fatin
- 9 Architecture - Image Encoder
- 10 Architecture - DAMSM loss
- 11 Experiments - Datasets
- 12 Experiments - Evaluation • Inception score
- 13 Experiments - Component Analysis
- 14 Experiments - Qualitative (CUB)
- 15 Experiments - Novel scenarios
- 16 Experiments - Failure cases Did not capture global coherent structure
