EN.601.783 Vision as Bayesian Inference

EN.601.783

Vision as Bayesian Inference

Tues/Thurs: 9:00-10:15 Spring 2023, Homewood Campus, Maryland 110

Course Description

This course models vision as Bayesian Inference. It concentrates on visual tasks such as segmenting images, detecting objects in images, and recognizing objects. Its goal is to describe the state of the art techniques. The handouts consist of copies of the lecture notes and related papers.

Important information

Instructor: Prof. Alan Yuille, ayuille1@jhu.edu. TA: Jieru Mei(meijieru@jhu.edu), Yutong Bai(ybai20@jh.edu), CA: Junfei Xiao (junfei.xiao@jhu.edu) and Qihao Liu (qliu45@jhu.edu).
Piazza discussion site [Piazza Course Site] We encourage the students to post questions about the course and homeworks on Piazza.
Grading Plan: (tentative) 4 or 5 homework assignments (to be posted here) + participation points (counted as another homework). Late homework will not be accepted unless permission is obtained well in advance in documented extenuating circumstances. Please email Prof. Yuille (ayuille1@jhu.edu) for approval and cc TAs. Participation points are given based on in-class / Piazza questions.
To encourage participation, we will split you into several groups. Each group can meet offline to discuss about the course material and ask questions during each lecture. Details can be found in the following Online Plan.
Please read [The Online Plan] on details about lecture strategies, participation, homework and assistance.

Reading Material

Course Notes and Handouts.
Papers and Journal Articles.

Tentative Schedule

Lecture	Topics	Handouts	Supplements	Additional Readings
1 (01/24/2023)	Introduction	Lecture1
2 (01/26/2023)	Image Representation and PCA Sparsity	Lecture2	Lecture2 Notes	Eigenfaces Robust Face Recognition Sparse Representation
3 (01/31/2023)	Dictionaries, Mixtures of Gaussians, Mini‐Epitomes, EM	Lecture3 (1) Lecture3 (2)		K-means++ Mini-Epitomes
4 (02/02/2023)	Super Pixels and Variational Models	Lecture4	Lecture4 Notes	ProtoObjects SLIC
5 (02/07/2023)	Image Statistics and Weak Membrane Models	Lecture5	Lecture5 Notes	NonLinearTotalVariation StatisticsImagePatches LevelSet
6 (02/09/2023)	Edge Detection and Simple Semantic Segmentation	Lecture6 Part1 Lecture6 Part2 Lecture6 Part3		EdgeDetection SemanticSegmentation LinearFiltering NonLinearFiltering
7 (02/14/2023)	Decision Theory	Lecture7 Part1 Lecture7 Part2 Lecture7 Part3 Lecture7 Part4	Lecture7 Notes
8 (02/16/2023)	Deep Networks and Edge Detection	Lecture8 Part1 Lecture8 Part2 Lecture8 Part3		Holistically-Nested Edge Detection
9 (02/21/2023)	MRF-MFT and Semantic Segmentation	Lecture9 Part1 Lecture9 Part2 Lecture9 Part3		DeepLab Fully Connected CRF BeliefPropagationMFT SmirnakisYuille1994
10 (02/23/2023)	Weak Membrane, MRF and Annealing	Lecture10 Part1 Lecture10 Part2 Lecture10 Part3		Image Segmentation CPMC Grab Cut
11 (02/28/2023)	GrabCut and Belief Propagation	Lecture11 Part1 Lecture11 Part2		Tutorial on Bayesian Inference
12 (03/02/2023)	Probabilities on Graphs	Lecture12 Part1 Lecture12 Part2		BayesianStereo Occlusions and Binocular Stereo Stereo BP Stereo CNN
13 (03/08/2021)	Stereo and Boltzmann Machine	Lecture13 Part1 Lecture13 Part2		Random Field Learning Exponential Models FRAME
14 (03/09/2023)	Learning Exponential Models, Hidden Markov Models	Lecture14: HMM Lecture14: BoltzmannMachine		HMM Math Details Chang Peng et al 2002
15 (03/14/2023)	Lighting	Lecture15 Part1 Lecture15 Part2		Lambertian Lighting SVD and Integrability KGBR Lambertian Reflectance
16 (03/14/2023)	AdaBoost	Lecture16 Part1 Lecture16 Part2	Lecture Notes Math Details	Text Detection Object Detection
17 (03/16/2023)	Support Vector Machine	Lecture17 Part1		Latent SVM Strang Nonlinear Optimization Yuille & He 2013
Spring Break on 03/18/2023 to 03/26/2023
18 (03/28/2023)	Deformable Part Model	Lecture18 Part1 Lecture18 Part2
19 (03/30/2023)	Compositional Model	Lecture 19		Paper 1 Paper 2 Paper 3
20 (04/04/2023)	Parsing	Lecture 20		CompNet Paper1 CompNet Paper2 Human Parsing
21 (04/06/2023)	Compositional Generative Networks	Lecture 21 Part 1 Lecture 21 Part 2		Semantic Parts You Only Annotate Once
22 (04/11/2023)	Deep Networks Attacks and Understanding	Lecture 22		Paper1 Paper2
23 (04/13/2023)	Computer Graphics and Computer Vision	Lecture 23		SemanticPartsCGViewpoint VirtualHorsesTigers
24 (04/18/2023)	Model Robustness and Beyond	Lecture 24 Part1 Lecture 24 Part2 Lecture 24 Part3
25 (04/20/2023)	Analysis By Synthesis	Lecture 25		Image Parsing 1 Image Parsing 2 Image Parsing 3 Region Competition
26 (04/25/2023)	GAN	Lecture 26 Part1 Lecture 26 Part2		Paper 1 Paper 2 Paper 3 Paper 4 Paper 5