Schedules

[L1] Introduction to Computer Vision

[L2] Representation Learning; Convolutional Neural Networks

University Closed

[L3] Building Blocks in Deep Learning

[L4] Convolutional Neural Network Architectures

[L5] Advanced CNN Models; Transformers

[L6] Vision Transformer; Advanced Vision Transformers

[L7] Efficient Transformers; Other Advanced Architectures

[L8]  Encoder-Decoder Architectures; Transformer Encoder-Decoder

[L9] Object Detection; Semantic Segmentation

[L10] Detection Transformer (DETR); Robustness in Computer Vision

[L11] (Invited Lecture) Towards A Better Camera (Dr. Jian Wang, Snap Research)

[L12] Robustness in CV; Generative Models Basics

[L13] Deep Generative Models; Autoregressive Models and Autoencoders

[L14] Variational Autoencoders (VAEs); Vector Quantized VAEs

[L15] Generative Adversarial Networks (GANs)

Spring Break

Spring Break

[L16] Denoising Diffusion Diffusion Models

[L17] Diffusion Model Applications

[L18] (Invited Lecture) 3D Vision: Reconstruction and Generation (Dr. Yuhao Wang, Univeristy of Waterloo)

[L19] Diffusion Models Applications

[L20] Introduction to LLMs and Vision-Language Models

[L21] Instruction fine-tuning and parameter-efficient fine-tuning

[L22] Post-Training Techniques 1: Hallucination, Alignment, and RAG

[L23] (Invited Lecture) Post-Training Techniques 2: In-Context Learning, Reasoning and Planning

[L24] Applications / LLM and VLM Agents

[L25] (Invited Lecture) Applications (Robotics)

[L26] Final Presentation Session 1

[L27] Final Presentation session 2

[L28] Final Presentation Session 3

Finals Week; No Class