COMPSCI 670 | Schedule

Date	Lecture	Readings	Logistics
2/1	Lecture #1 (Grant): Introduction and logistics	Szeliski book, Chapter 1 The speed of processing in the human visual system, Thorpe et al., 1996	Setup Piazza, Gradescope
Module 1: Image Formation and Representation
2/6	Lecture #2 (Grant): Radiometry	Surface reflectance estimation and natural illumination statistics, Dror et al., 2001. Chapter 2.2 and 2.3 of Forsyth and Ponce, online here (Section 3.5 and 3.6) NeRF	HW1 out (due 2/20)
2/8	Lecture #3 (Grant): Light and color	Szeliski book, Chapter 2 Forsyth and Ponce, Chapter 3 Basic Color Terms : Their Universality and Evolution, Berlin and Kay, 1969 (book, Wikipedia article) Beau Lotto's TED talk
2/9	Lecture #4 (Max, Fabien): Python tutorial (Friday, 2-3pm)	Collab page	CS 150/151
2/13	Lecture #5 (Grant): Light and color; Image formation	Szeliski book, Chapter 2
2/15	Lecture #6 (Grant): Image formation	Szeliski book, Chapter 2 Wikipedia article on camera Light stages at USC
Module 2: Basic Image Processing
2/20	Lecture #7 (Grant): Modeling images	Forsyth and Ponce, Chapter 6.3 & 6.4 Texture synthesis by non-parametric sampling, Efros and Leung, 99 Non-local means denoising, Buades et al., 11 OpenAI DALL·E 3 and ChatGPT	HW2 out (due 3/5)
2/22	No class
2/27	Lecture #8 (Grant): Linear filtering	Szeliski book, Chaper 3 Hybrid images Berkeley segmentation dataset
Module 3: Correspondence, Alignment, Geometry
2/29	Lecture #9 (Grant): Optical flow	Lucas-Kanade optical flow Middlebury stereo dataset Szeliski book, Chapter 9
3/5	Lecture #10 (Grant): Feature detection and matching	Szeliski book, Chapter 7.1
3/7	Lecture #11 (Grant): Image transformations and alignment	Szeliski book, Chapter 8.1
3/12	Lecture #12 (Grant): Applications of image alignment	Szeliski book, Chapter 8.2 & 11 VGG image search	HW3 out (due 4/2)
Module 4: Fundamentals of Neural Networks
3/14	Lecture #13 (Grant): Intro to recognition	Visual categorization with bag of keypoints, Csurka et al., 2004 Histogram of Oriented Gradients, Dalal & Triggs, 2005 Textons, the elements of texture perception, and their interactions, Julesz, 1981 Computer vision datasets (via Roboflow)
3/19	No class (Spring recess)
3/21	No class (Spring recess)
3/26	Lecture #14 (Grant): Linear models	Perceptron paper, McColloch & Pitts, 1943 Linear classifier, Wikipedia
3/28	Lecture #15 (Grant): Neural networks	LeNet, AlexNet ImageNet OpenAI Microscope (model visualizer) Pytorch CNN tutorial
4/2	Lecture #16 (Grant): Neural networks		HW4 out (due 5/2)
Module 5: Advanced Topics in Recognition
4/4	Lecture #17 (Grant): Transfer learning	CNNs off-the-shelf, Razavian et al., 2014 Deep Filter Banks, Cimpoi et al., 2015 Bilinear CNNs, Lin et al., 2015 Taskonomy, Zamir et al., 2018 Task2Vec, Achille et al., 2019 Task2Box, Daroya et al., 2024
4/9	Lecture #18 (Grant, remote): Project feedback
4/11	Lecture #19 (Grant, remote): Project feedback
4/16	Lecture #20 (Grant): Transfer learning
4/18	Lecture #21 (Grant): Object detection	Dalal & Triggs, Poselets, Selective search R-CNN, Fast R-CNN, Faster R-CNN YOLO, SSD
4/23	Lecture #22 (Grant): Object detection; Image segmentation	Mask R-CNN, He et al., ICCV 2017 Fully convolutional networks, Long & Shelhamer et al., CVPR 15 UNet, Ronneberger et al., MICCAI 15 Panoptic FCN, Kirillov et al., CVPR 19
4/25	Lecture #23 (Grant): Image generation	Inverting deep representations, Mahendran & Vedaldi, 2014 Texture synthesis & style transfer using CNNs, Gatys et al., 2015 Texture networks, Ulyanov et al., 2016 Visualizing deep texture representations, Lin & Maji, 2016 Generative adversarial networks, Goodfellow et al., 2020 (CACM version) Deep image prior, Ulyanov et al., 2017 Some theory on the deep image prior (DIP as a Gaussian process, Spectral bias of DIP)
4/30	Lecture #24 (Grant): Image generation
5/2	Lecture #25 (Grant): Unsupervised learning	Colorization - Zhang et al., 2016, Larsson et al., 2016 Context prediction - Doersch et al., 2015 Jigsaw puzzle - Noroozi & Favaro, 2016 Image rotation - Gidaris et al., 2018 Instance discrimination - Dosovitskiy et al., 2015, Xu et al., 2018, MOCO, SimCLR, BYOL 3D - PointContrast, Convex Decomposition Audio - Owens et al., 2016 Video correspondence Jabri et al., 2020, Future prediction Walker et al., 2016 Generative modeling - RepurposingGANs 2021, DatasetGAN 2021 Generative or Contrastive? Saha et al., 22
5/7	Lecture #26 (Grant): Unsupervised learning
5/9	Lecture #27 (Grant): 3D shape understanding	Multi-view CNN VoxNet, O-CNN PointNet, Deep Sets, PointNet++, SplatNet A deeper look at 3D classifiers, Su et al. 18
5/10	Poster presentations (CS 150/151) (Friday)