Deep Learning for Computer Vision

This contains my complete notes from the course Deep Learning for Computer Vision (Stanford CS231n) I took in the spring semester of my sophomore year.

CV | Lecture 14 Generative Models 2

GAN, Diffusion models, Classifier-free guidance, Latent Diffusion Models, Diffusion Transformer

CV | Lecture 13 Generative Models 1

Autoregressive models, VAE, ELBO

CV | Lecture 12 Self Supervised Learning

introduction, masked autoencoders, SimCLR, MoCo, CPC

CV | Lecture 11 Large Scale Distributed Training

data parallelism, activation checkpointing, other parallelism

CV | Lecture 10 Video Understanding

temporal modeling, self attention for videos, multimodal video understanding

CV | Lecture 9 Object Detection, Image Segmentation, Visualizing

in-network unsampling, object detection, instance segmentation, visualization

CV | Lecture 8 Attention and Transformers

self-attention, transformers, ViT, tweaks of transformers

CV | Lecture 7 Recurrent Neural Networks

sequence modeling, RNN, applications, LSTM, morden RNNs

CV | Lecture 6 CNN Architectures

CNN structure, CNN training

CV | Lecture 5 Image Classification with CNNs

Convolutional Networks, convolution layer, pooling layers