Computer Vision Course Syllabus

Books

TIF - Foundations of Computer Vision by Antonio Torralba, Phillip Isola and William T. Freeman. Free online. Covers the latest deep learning applications including diffusion models.

BISHOP - Deep Learning - Foundations and Concepts by C. Bishop and H. Bishop. Available to view online from the book’s website.

SZELINSKI - Computer Vision: Algorithms and Applications, 2nd Edition. Free to download for personal use. Alternative to TIF for some topics.

Some of the assigned reading sits on the O’Reilly platform, which your university provides at no cost. See O’Reilly access if you have not signed in yet.

Planned Schedule

Part I: Detection and Segmentation

Week	Topic	Description
1	Introduction	Computer vision for agents with egomotion. Prerequisites review: Python, linear algebra, probability theory, camera fundamentals. Reading: TIF Chapter 1
2	Statistical Learning Theory	End-to-end prediction, featurization, fully connected neural architectures, maximum likelihood optimization. Reading: TIF Chapters 9-10, BISHOP Chapters 4-5
3	Dense Neural Networks	Cross entropy loss, training and regularization of dense layers. Reading: TIF Chapters 12-13, BISHOP Chapter 6
4	CNNs	Spatial feature hierarchies, image classification, ResNets for real-time perception. Reading: TIF Chapter 24, BISHOP Chapter 10
5	Object Detection	YOLO and Faster R-CNN architectures for identifying and locating objects. Reading: TIF Chapter 50
6	Semantic Segmentation	Pixel-level labeling, panoptic segmentation for full scene understanding. Reading: SZELINSKI Chapter 6
7	Midterm Exam	Covers Weeks 1-6.
8	Transformers and Vision Transformers	Self-attention for global image dependencies, ViT against CNN trade-offs. Reading: BISHOP Chapter 12, TIF Chapter 26

Part II: Vision Language Models (VLMs)

Week	Topic	Description
9	Contrastive Learning	Vision-language pretraining, CLIP for relating images and text. Reading: CLIP paper, TIF Chapter 51
10	VLM Finetuning	BLIP-2, LLaVA for image captioning and Visual Question Answering.
11	Prompted Vision Models	Meta’s SAM as a worker receiving multimodal prompts from VLM planners.

Part III: Generative Vision Models

Week	Topic	Description
12	Neural 3D Scene Representations	NeRF for creating 3D scenes from 2D images, volume rendering concepts. Reading: TIF Chapter 45
13	Diffusion Models and Review	Physics-inspired learning, conditional image generation, DALL-E and Stable Diffusion, then final exam preparation. Reading: TIF Chapters 32, 34

Edit this page on GitHub or file an issue.

Course

Assignments

MIT Book Code

Study Guides

Computer Vision Course Syllabus

Books

Planned Schedule

Part I: Detection and Segmentation

Part II: Vision Language Models (VLMs)

Part III: Generative Vision Models

​Books

​Planned Schedule

​Part I: Detection and Segmentation

​Part II: Vision Language Models (VLMs)

​Part III: Generative Vision Models

Books

Planned Schedule

Part I: Detection and Segmentation

Part II: Vision Language Models (VLMs)

Part III: Generative Vision Models