Learning Outcomes

Topic	Note
Object Detection & Segmentation (CNN)
Generative Models & Generative Adversarial Networks	GAN
Transfer Learning for Visual Classification & Synthesis	Transfer Learning
Recurrent Neural Networks	RNN
Transformer	Transformer
Meta-Learning for Visual Analysis	Meta-Learning
Self-Supervised Learning for Visual Analysis	Self-Supervised Learning
Beyond 2D Vision (3D and Depth)	3D and Depth
Vision and Language	Vision and Language

Implementation

Task	Method	Code
Principal Component Analysis	PCA	code
Image classification	Inception-V3	code
Image semantic segmentation	Fully Convolution Networks	code
Face image generation	DC-GAN	code
Conditional image synthesis and Feature Disentanglement	AC-GAN	code
Domain Adaptation	DANN	code
Image Classification with Vision Transformer	Vision Transformer	code
Visualization in Image Captioning	Vision Transformer	code