Scribd
Upload
182 views1 page

Syllabus For CSCI 631 - Foundations of Computer Vision

This syllabus outlines a graduate level course on computer vision over 15 weeks. It covers fundamental topics like linear filters, edge detection, and interest points. It then moves into more advanced deep learning models like convolutional neural networks, recurrent neural networks, sequence to sequence models, attention networks, and generative adversarial networks. Guest speakers will discuss specific CNN architectures and applications. Students will complete programming assignments applying concepts from each section and present final projects at the end of the course.

Uploaded by

ddkk
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
182 views1 page

Syllabus For CSCI 631 - Foundations of Computer Vision

This syllabus outlines a graduate level course on computer vision over 15 weeks. It covers fundamental topics like linear filters, edge detection, and interest points. It then moves into more advanced deep learning models like convolutional neural networks, recurrent neural networks, sequence to sequence models, attention networks, and generative adversarial networks. Guest speakers will discuss specific CNN architectures and applications. Students will complete programming assignments applying concepts from each section and present final projects at the end of the course.

Uploaded by

ddkk
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Syllabus for CSCI 631 - Foundations of Computer Vision

CLASS # Date Topic Readings/Speakers Homework

1 Thursday Aug 20 Introduction - Logistics, linear filters

2 Tuesday Aug 25 Convolution + Linear filters

3 Thursday Aug 27 Linear Filters + Edge detection HW1 - Linear filters

4 Tuesday Sep 01 Interest points

5 Thursday Sep 03 Interest points HW2 - Feature matching

6 Tuesday Sep 08 Texture and color

7 Thursday Sep 10 Texture and color HW3 - Classification with features

8 Tuesday Sep 15 Clustering Ranninger and Malik paper

9 Thursday Sep 17 Clustering

10 Tuesday Sep 22 Classifiers -and loss minimization- SVM, cross-entropy

11 Thursday Sep 24 The perceptron/Logistic regression/

12 Tuesday Sep 29 Neural networks and back prop HW4 - Hand-code NN with backprop

13 Thursday Oct 01 CNN and early image networks

14 Tuesday Oct 06 Backprop for CNN Guest speaker - Timothy Zee

15 Thursday Oct 08 CNN Interpretability Guest speaker - Timothy Zee

16 Tuesday Oct 13 Classification and Regression Networks YannLeCun CNN/Science paper HW5 - VGG implementation

17 Thursday Oct 15 RNN + LSTM

18 Tuesday Oct 20 Sequence to sequence model (captioning) Final project proposal

19 Thursday Oct 22 Attention networks

20 Tuesday Oct 27 Object detection

21 Thursday Oct 29 More on CNN applications

22 Tuesday Nov 03 ResNet and Inception Gkioxaris Mask-RNN paper

23 Thursday Nov 05 Advanced CNN models

24 Tuesday Nov 10 GANs Posters (no results needed)

25 Thursday Nov 12 Ethics in computer vision

26 Tuesday Nov 17 Poster presentation

27 Thursday Nov 19 Poster presentation

27 Tuesday Nov 24 LAST DAY OF CLASSES

28 Nov 26-27 No class - Thanksgiving break

FINALS

Monday Nov 30 READING DAY

Wednesday Dec 02 FINAL REPORTS DUE @ MIDNIGHT This can change

You might also like