{"id":1609,"date":"2022-10-01T10:20:05","date_gmt":"2022-10-01T13:20:05","guid":{"rendered":"http:\/\/cs.smu.ca\/~jiju\/?page_id=1609"},"modified":"2023-03-28T21:04:34","modified_gmt":"2023-03-29T00:04:34","slug":"csci-4472-deep-learning-for-computer-vision","status":"publish","type":"page","link":"https:\/\/cs.smu.ca\/~jiju\/index.php\/csci-4472-deep-learning-for-computer-vision\/","title":{"rendered":"CSCI 4472: Deep Learning for Computer Vision"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\"><strong>Course Description<\/strong><\/h2>\n\n\n\n<p>Students are introduced to deep learning fundamentals and architectures with a focus on computer vision tasks such as image classification, object detection, image segmentation, image synthesis, and 3D reconstruction. Relevant case studies will be discussed. Students will learn to build neural networks for computer vision problems using Python and Tensorflow. Upon completion of the course, students will be able to: <\/p>\n\n\n\n<ul><li> Describe and implement basic image processing tasks such as filtering, edge and feature detection<\/li><li>Develop computer vision applications using OpenCV and python <\/li><li>Describe the deep learning fundamentals <\/li><li>Understand convolutional neural networks and use it in high level computer vision applications such as image classification, recognition and object detection<\/li><li>Use Tensorflow to design and develop neural networks for vision applications<\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Course Administration<\/h2>\n\n\n\n<h4 class=\"wp-block-heading\"><strong><span style=\"color:#ff6663\" class=\"tadv-color\">Instructor<\/span><\/strong><\/h4>\n\n\n\n<p>Dr. Jiju Poovvancheri (e-mail:jiju.poovvancheri@smu.ca)<\/p>\n\n\n\n<h4 class=\"wp-block-heading\"><strong><span style=\"color:#ff6663\" class=\"tadv-color\">Lectures<\/span><\/strong><\/h4>\n\n\n\n<ul><li>Mondays (10:00am-11:15am) -LA 181<\/li><li>Wednesdays (10:00am-11:15am)-LA 181<\/li><\/ul>\n\n\n\n<h4 class=\"wp-block-heading\"><strong><span style=\"color:#ff6663\" class=\"tadv-color\">Recitations<\/span><\/strong><\/h4>\n\n\n\n<ul><li>Wednesdays (11:30am-12:45pm)- SB 155<\/li><\/ul>\n\n\n\n<h4 class=\"wp-block-heading\"><strong><span style=\"color:#ff6663\" class=\"tadv-color\">Office Hours (via MS Teams)<\/span><\/strong><\/h4>\n\n\n\n<ul><li>Mondays (11:30 am -1:30 pm) <\/li><li>Wednesdays (1:00 &#8211; 2:00 pm) <\/li><li>Fridays (10:30 am-1:30 pm) <\/li><\/ul>\n\n\n\n<h4 class=\"wp-block-heading\"><strong><span style=\"color:#ff6663\" class=\"tadv-color\">Course Pages<\/span><\/strong><\/h4>\n\n\n\n<ul><li><strong><a rel=\"noreferrer noopener\" href=\"https:\/\/teams.microsoft.com\/l\/team\/19%3adrnI2KUn3Rik_r4HbHM9OKOiuOZcxvVg7NN8t7Jo-kw1%40thread.tacv2\/conversations?groupId=3a3d4b16-b48b-4d64-8db9-992c91b4549b&amp;tenantId=060b02ae-5775-4360-abba-e2e29cca6627\" target=\"_blank\">MS Class Teams<\/a><\/strong><a rel=\"noreferrer noopener\" href=\"https:\/\/teams.microsoft.com\/l\/team\/19%3aPy4adcju8TwskpHR0tH5ST0lArWCsd12x-VTZBnBWwQ1%40thread.tacv2\/conversations?groupId=33ab7177-b5d3-4dcb-a990-af0054d026c1&amp;tenantId=060b02ae-5775-4360-abba-e2e29cca6627\" target=\"_blank\"> <\/a>(Lecture slides, discussion forum, grades)<\/li><li><strong><a href=\"https:\/\/github.com\/jijup\/CV-Lab\" target=\"_blank\" rel=\"noreferrer noopener\">Github<\/a><\/strong> (Set up &amp; installation info, links to software libraries, starter codes of lab exercises &amp; assignments)<\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Tentative Schedule<\/strong> <strong>(Fall 2022)<\/strong><\/h2>\n\n\n\n<div class=\"wp-block-columns has-3-columns is-layout-flex wp-container-4\">\n<div class=\"wp-block-column is-layout-flow\">\n<p class=\"has-text-align-center\"><strong>Date<\/strong><\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<p class=\"has-text-align-center\"><strong>Topic<\/strong><\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<p class=\"has-text-align-center\"><strong>Projects<\/strong><\/p>\n<\/div>\n<\/div>\n\n\n\n<h5 class=\"has-text-align-center wp-block-heading\"><strong>Low level Vision<\/strong><\/h5>\n\n\n\n<div class=\"wp-block-columns has-3-columns is-layout-flex wp-container-8\">\n<div class=\"wp-block-column is-layout-flow\">\n<p>Sept. 7<\/p>\n\n\n\n<p>Sept. 12<\/p>\n\n\n\n<p>Sept. 14<\/p>\n\n\n\n<p>Sept. 21<\/p>\n\n\n\n<p>Sept. 28<\/p>\n\n\n\n<p>Oct. 3<\/p>\n\n\n\n<p>Oct. 5<\/p>\n\n\n\n<p>Oct. 12<\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<p>Introduction to the course<\/p>\n\n\n\n<p>Image Formation<\/p>\n\n\n\n<p>Spatial Filters<\/p>\n\n\n\n<p>Non-linear Filters (Bilateral)<\/p>\n\n\n\n<p>Image Gradients, Canny Edge<\/p>\n\n\n\n<p>Feature Detection (Harris)<\/p>\n\n\n\n<p>SIFT Descriptor, Matching<\/p>\n\n\n\n<p>Mid term Test<\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<p>   <\/p>\n\n\n\n<p><\/p>\n\n\n\n<p>Project 1: Hybrid Images<\/p>\n\n\n\n<p><\/p>\n\n\n\n<p>Project 2: Feature Matching<\/p>\n\n\n\n<p><\/p>\n<\/div>\n<\/div>\n\n\n\n<h5 class=\"has-text-align-center wp-block-heading\">Deep Learning Fundamentals<\/h5>\n\n\n\n<div class=\"wp-block-columns has-3-columns is-layout-flex wp-container-12\">\n<div class=\"wp-block-column is-layout-flow\">\n<p>Oct. 17<\/p>\n\n\n\n<p>Oct. 19<\/p>\n\n\n\n<p>Oct. 24<\/p>\n\n\n\n<p>Oct. 26<\/p>\n\n\n\n<p>Oct. 31<\/p>\n\n\n\n<p>Nov. 2<\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<p>Supervised Learning<\/p>\n\n\n\n<p>Feed Forward NN<\/p>\n\n\n\n<p>Gradient Descent and Variants<\/p>\n\n\n\n<p>Backpropagation<\/p>\n\n\n\n<p>Regularization, Training<\/p>\n\n\n\n<p>Convolutional Neural networks<\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<p><\/p>\n\n\n\n<p>Project 3: Binary Classifier<\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n<\/div>\n<\/div>\n\n\n\n<h5 class=\"has-text-align-center wp-block-heading\">High level Computer Vision<\/h5>\n\n\n\n<div class=\"wp-block-columns has-3-columns is-layout-flex wp-container-16\">\n<div class=\"wp-block-column is-layout-flow\">\n<p>Nov. 14<\/p>\n\n\n\n<p>Nov. 16<\/p>\n\n\n\n<p>Nov. 21<\/p>\n\n\n\n<p>Nov. 23<\/p>\n\n\n\n<p>Nov. 28<\/p>\n\n\n\n<p>Nov. 30<\/p>\n\n\n\n<p>Dec. 5<\/p>\n\n\n\n<p>Dec. 7<\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<p>Image Classification<\/p>\n\n\n\n<p>CNN Architectures<\/p>\n\n\n\n<p>Object Detection -R-CNN<\/p>\n\n\n\n<p>Face Detection (Siamese Networks)<\/p>\n\n\n\n<p>Object Detection -YOLO<\/p>\n\n\n\n<p>Segmentation<\/p>\n\n\n\n<p>Point Clouds, 3D Reconstruction<\/p>\n\n\n\n<p>Review<\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<p><\/p>\n\n\n\n<p>Project 4: Digit Recognition<\/p>\n\n\n\n<p><\/p>\n\n\n\n<p>Project 5: Face Recognition<\/p>\n\n\n\n<p><\/p>\n<\/div>\n<\/div>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Recitations<\/strong> <strong>(Tentative schedule)<\/strong><\/h2>\n\n\n\n<ul><li>Recitations 1 &#8211; 2- <a rel=\"noreferrer noopener\" href=\"https:\/\/github.com\/jijup\/CV-Lab\/blob\/master\/Hybrid_Images\/Hybrid_images_activities.ipynb\" target=\"_blank\"><strong>Image Filtering (Hybrid Images)<\/strong><\/a><\/li><li>Recitations 3-5- <a rel=\"noreferrer noopener\" href=\"https:\/\/github.com\/jijup\/CV-Lab\/blob\/master\/Feature_Match\/Feature_match_activities.ipynb\" target=\"_blank\"><strong>Feature Matching<\/strong><\/a><\/li><li>Recitations 6-8- <strong><a rel=\"noreferrer noopener\" href=\"https:\/\/github.com\/jijup\/CV-Lab\/blob\/master\/Binary_Classifier\/Binary_classifier_activities_v1.ipynb\" target=\"_blank\">Binary Classifier<\/a><\/strong><\/li><li>Recitations 8-9-<a rel=\"noreferrer noopener\" href=\"https:\/\/github.com\/jijup\/CV-Lab\/blob\/master\/Digit_Recognition\/MNIST_Digit_Recognition_activities.ipynb\" target=\"_blank\"><strong>Digit Recognition (MNIST)<\/strong><\/a><\/li><li>Recitations 9-11- <strong><strong><a href=\"https:\/\/github.com\/jijup\/CV-Lab\/blob\/master\/Face_Recognition\/Face_Recognition_Activities.ipynb\" target=\"_blank\" rel=\"noreferrer noopener\">Face Recognition<\/a><\/strong><\/strong><\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Grading<\/strong><\/h2>\n\n\n\n<div class=\"wp-block-columns has-2-columns is-layout-flex wp-container-22\">\n<div class=\"wp-block-column is-layout-flow\">\n<p><strong>Projects (40%)<\/strong> <\/p>\n\n\n\n<div class=\"wp-block-columns has-2-columns is-layout-flex wp-container-19\">\n<div class=\"wp-block-column is-layout-flow\"><\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\"><\/div>\n<\/div>\n\n\n\n<p><\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<ul><li>There will be five programming projects.<\/li><li>The programming problems will involve python programming using OpenCV and Tensorflow libraries<\/li><li>Each project carries 10% weightage.<\/li><li> Lowest grade will be dropped<\/li><li>Each project will be evaluated during the recitations<\/li><li>The students will get two recitations to complete each project.<\/li><li>Attendance in recitations is mandatory to get the project marks.<\/li><\/ul>\n\n\n\n<p><\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns has-2-columns is-layout-flex wp-container-25\">\n<div class=\"wp-block-column is-layout-flow\">\n<p><strong>Midterm(20%)<\/strong><\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<p><\/p>\n\n\n\n<ul><li>There will be one mid term exam (closed book). The tests will be conducted in the second week of October 2022 <\/li><li>Used to evaluate your knowledge of course contents.<\/li><li>To be held during the lecture hour.<\/li><li>If you miss the quiz for any reason: (1) You must contact your instructor within 48 hours, and (2) You will be required to fill out and submit a <a rel=\"noreferrer noopener\" href=\"https:\/\/www.smu.ca\/webfiles\/DeclarationofExtenuatingCircumstances.pdf\" target=\"_blank\">Declaration of extenuating Circumstances form<\/a>.<\/li><\/ul>\n\n\n\n<p><\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns has-2-columns is-layout-flex wp-container-28\">\n<div class=\"wp-block-column is-layout-flow\">\n<p><strong>Final Exam (40%)<\/strong><\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<ul><li>Saint Mary&#8217;s University ID is required.<\/li><li>The final is open book with no electronics allowed.<\/li><li>Scheduled by the Registrar during the formal exam period.<\/li><li>Cumulative and will cover all material discussed in the course.<\/li><li>You must pass the final exam to pass the course.<\/li><\/ul>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n<\/div>\n<\/div>\n\n\n\n<p>Notes:&nbsp;&nbsp;<br>The final mark will be a letter grade based on the scale described in Section 5 of the Academic Regulations in the University Calendar. There is no curving of grades, or grading based on rank (e.g., a certain number of \u201cA\u201d grades, etc.). Final grades are truncated to 1 decimal place and then rounded (.5 to .9 are rounded up, .0 to .4 are rounded down) to the nearest whole number.&nbsp;There will be no supplementary examinations.&nbsp; <\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Text Books<\/strong><\/h2>\n\n\n\n<div class=\"wp-block-columns has-2-columns is-layout-flex wp-container-31\">\n<div class=\"wp-block-column is-layout-flow\"><\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<p><strong>Required: Computer Vision: Algorithms and Applications, 2nd Edition<\/strong><br>Richard Szelski<br>Wiley<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns has-2-columns is-layout-flex wp-container-34\">\n<div class=\"wp-block-column is-layout-flow\">\n<p><\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<p><strong>Reference: Computer Vision: A Modern Approach<\/strong>, 2nd Edition,<br>David Forsyth and Jean Ponce  <br>Pearsoned<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns has-2-columns is-layout-flex wp-container-37\">\n<div class=\"wp-block-column is-layout-flow\">\n<p><\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow\">\n<p><strong>Reference: Deep Learning<\/strong><br>Ian Goodfellow, Yoshua Bengio and Aaron Courville<br>MIT Press <\/p>\n<\/div>\n<\/div>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Course Description Students are introduced to deep learning fundamentals and architectures with a focus on computer vision tasks such as&hellip;<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":[],"_links":{"self":[{"href":"https:\/\/cs.smu.ca\/~jiju\/index.php\/wp-json\/wp\/v2\/pages\/1609"}],"collection":[{"href":"https:\/\/cs.smu.ca\/~jiju\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/cs.smu.ca\/~jiju\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/cs.smu.ca\/~jiju\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/cs.smu.ca\/~jiju\/index.php\/wp-json\/wp\/v2\/comments?post=1609"}],"version-history":[{"count":20,"href":"https:\/\/cs.smu.ca\/~jiju\/index.php\/wp-json\/wp\/v2\/pages\/1609\/revisions"}],"predecessor-version":[{"id":1668,"href":"https:\/\/cs.smu.ca\/~jiju\/index.php\/wp-json\/wp\/v2\/pages\/1609\/revisions\/1668"}],"wp:attachment":[{"href":"https:\/\/cs.smu.ca\/~jiju\/index.php\/wp-json\/wp\/v2\/media?parent=1609"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}