YoVDO

TransGAN - Two Transformers Can Make One Strong GAN - Machine Learning Research Paper Explained

Offered By: Yannic Kilcher via YouTube

Tags

Generative Adversarial Networks (GAN) Courses Machine Learning Courses Computer Vision Courses Data Augmentation Courses Transformer Architecture Courses Self-Attention Courses

Course Description

Overview

Explore a comprehensive video explanation of the machine learning research paper "TransGAN: Two Transformers Can Make One Strong GAN." Delve into the groundbreaking approach of using transformer-based architectures for both the generator and discriminator in Generative Adversarial Networks (GANs). Learn about the innovative techniques employed, including data augmentation with DiffAug, super-resolution co-training, and localized initialization of self-attention. Discover how TransGAN achieves competitive performance with convolutional GANs on various datasets and gain insights into the future potential of transformer-based GANs in computer vision tasks.

Syllabus

- Introduction & Overview
- Discriminator Architecture
- Generator Architecture
- Upsampling with PixelShuffle
- Architecture Recap
- Vanilla TransGAN Results
- Trick 1: Data Augmentation with DiffAugment
- Trick 2: Super-Resolution Co-Training
- Trick 3: Locality-Aware Initialization for Self-Attention
- Scaling Up & Experimental Results
- Recap & Conclusion


Taught by

Yannic Kilcher

Related Courses

Transformers: Text Classification for NLP Using BERT
LinkedIn Learning
TensorFlow: Working with NLP
LinkedIn Learning
Nyströmformer- A Nyström-Based Algorithm for Approximating Self-Attention
Yannic Kilcher via YouTube
Recreate Google Translate - Model Training
Edan Meyer via YouTube
Let's Build GPT - From Scratch, in Code, Spelled Out
Andrej Karpathy via YouTube