Vibhas Vats

Vibhas Vats

Computer Science Ph.D candidate at Indiana University

Teaching

Course Development and Instructor - Computer Vision Discussion Section

Graduate Level Course (B657), Indiana University Bloomington, Computer Science Department -- Luddy SICE, 2025

In spring 2024 and 2025, I taught the third and fourth iteration of the ‘Computer Vision - discussion section’ at Indiana University. I discuss a list of seminal papers exploring deep learning (DL) architectures. I designed the first iteration of the DL discussion section in Spring 2022, it is designed to explore the seminal papers exploring DL architectures to develop an intuitive as well as mathematical understanding of major concepts in DL. In 16 weeks, the course roughly covers major architectures in three broad sections, Convolution-based networks (CNNs), Multi-layer perceptron-based networks (MLPs), and Transformer-based networks (ViTs). In CNNs, we cover models like LeNet, AlexNet, GoogLeNet, ResNets, Wide ResNet, Stochastic ResNet, ResNeXt, DenseNet, ConvMixer, and Xception Net. In MLPs, we cover models like MLP Mixer, ResMLP, cycleMLP, and S^2 MLP model, and in ViTs, we cover models like Vision Transformer, DeiT, Swin Transformer, Local ViT, Convolutional-ViT, etc. We also explore shift operation-based networks. The class meets weekly with more than 150 students participating in the discussion. The list of papers covered in the discussion is below

Course Development and Instructor - Computer Vision Discussion Section

Graduate Level Course, Indiana University Bloomington, Computer Science Department, 2023

In spring 2023, I taught the second iteration of the ‘Computer Vision - discussion section’ at Indiana University. I discuss a list of seminal papers exploring deep learning (DL) architectures. I designed the first iteration of the DL discussion section in Spring 2022, it is designed to explore the seminal papers exploring DL architectures to develop an intuitive as well as mathematical understanding of major concepts in DL. In 16 weeks, the course roughly covers major architectures in three broad sections, Convolution-based networks (CNNs), Multi-layer perceptron-based networks (MLPs), and Transformer-based networks (ViTs). In CNNs, we cover models like LeNet, AlexNet, GoogLeNet, ResNets, Wide ResNet, Stochastic ResNet, ResNeXt, DenseNet, ConvMixer, and Xception Net. In MLPs, we cover models like MLP Mixer, ResMLP, cycleMLP, and S^2 MLP model, and in ViTs, we cover models like Vision Transformer, DeiT, Swin Transformer, Local ViT, Convolutional-ViT, etc. We also explore shift operation-based networks. The class meets weekly with more than 150 students participating in the discussion. The list of papers covered in the discussion is below

Course Development and Instructor - Computer Vision Discussion Section

Graduate Level Course, Indiana University Bloomington, Computer Science Department, 2022

In spring 2022, I designed and was the instructor for the first iteration of ‘Computer Vision - paper discussion section’ at Indiana University. The course was designed to explore the seminal papers on different architectures of deep-learning and computer vision. The course traced the history of development of Convolutional Neural Networks (like, LeNet, AlexNet, GoogLeNet, ResNets, Wide ResNet, Stochastic ResNet, ResNeXt, DenseNet, ConvMixer, Xception Net, etc.), Multi-layer Perceptron based networks (like, MLP Mixer, ResMLP, cycleMLP and S^2 MLP model), Transformer based Networks for vision application like, Vision Transformer, DeiT, Swin Transformer, Local ViT, CvT etc. papers) and other important architectures like SAN (self-attention Network), shift-based papers etc. The class met weekly with more than 130 students taking part in the discussion. Check the discussion schedule and slides for more details.