Neural Sync Active

BSDA5006 - Deep Learning for Computer Vision

Registry Synced

BSDA5006 - Deep Learning for Computer Vision

488 words

2 min read

Field	Value
Course Code	`BSDA5006`
Level	Degree Level Course
Credits	4
Type	Elective
Pre-requisites	None

📖 Description

-Knowledge of basics of image processing and computer vision -Knowledge of building blocks of deep learning including feedforward networks, convolutional neural networks, recurrent neural networks and transformers -Knowledge of generative AI models in computer vision -Knowledge of recent trends including explainability/zero-shot learning, few-shot learning, self-supervised learning, etc -Hands-on experience on implementation of basic image processing tasks -Hands-on experience on implementation of deep learning models for computer vision tasks -Hands-on experience on implementation of advanced computer vision tasks such as explainability, self-supervised learning, etc

🗓️ Weekly Syllabus

Week	Topic
Week 1	Introduction and Overview:
Course Overview and Motivation; Introduction to Image Formation, Capture and
Representation; Linear Filtering, Correlation,
Week 2	Visual Features and Representations:
Edge, Blobs, Corner Detection; Scale Space and Scale Selection; SIFT, SURF; HoG,LBP, etc.
Week 3	Visual Matching:
Bag-of-words, VLAD; RANSAC, Hough transform; Pyramid Matching; Optical Flow
Week 4	Deep Learning Review:
Review of Deep Learning, Multi-layer Perceptrons, Backpropagation
Week 5	Convolutional Neural Networks (CNNs):
Introduction to CNNs; Evolution of CNN Architectures: AlexNet, ZFNet, VGG,
InceptionNets, ResNets, DenseNets
Week 6	Visualization and Understanding CNNs:
Visualization of Kernels; Backprop-to-image/Deconvolution Methods; Deep Dream,
Hallucination, Neural Style Trans
Week 7	CNNs for Recognition, Verification, Detection, Segmentation:
CNNs for Recognition and Verification (Siamese Networks, Triplet Loss, Contrastive
Loss,
Week 8	Recurrent Neural Networks (RNNs):
Review of RNNs; CNN + RNN Models for Video Understanding: Spatio-temporal
Models, Action/Activity Recognition
Week 9	Attention Models:
Introduction to Attention Models in Vision; Vision and Language: Image Captioning,
Visual QA, Visual Dialog; Spatial Transformers; T
Week 10	Deep Generative Models:
Review of (Popular) Deep Generative Models: GANs, VAEs; Other Generative Models:
PixelRNNs, NADE, Normalizing Flows, etc
Week 11	Variants and Applications of Generative Models in Vision:
Applications: Image Editing, Inpainting, Superresolution, 3D Object Generation, Security;
Va
Week 12	Recent Trends:
Zero-shot, One-shot, Few-shot Learning; Self-supervised Learning; Reinforcement
Learning in Vision; Other Recent Topics and Application

📚 Books & Resources

Prescribed Books The following are the suggested books for the course:


        Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, 2016

        
        Michael Nielsen, Neural Networks and Deep Learning, 2016
        
        Yoshua Bengio, Learning Deep Architectures for AI, 2009
        
        Richard Szeliski, Computer Vision: Algorithms and Applications, 2010.
        
        Simon Prince, Computer Vision: Models, Learning, and Inference, 2012.
        
        David Forsyth, Jean Ponce, Computer Vision: A Modern Approach, 2002.

📝 About the Instructors

Prof. Vineeth N B

Professor,

Computer science and Engineering,

IIT Hyderabad

Source: https://study.iitm.ac.in/ds/course_pages/BSDA5006.html