COURSE OUTLINE: The automatic analysis and understanding of images and videos, a field called Computer Vision, occupies significant importance in applications including security, healthcare, entertainment, mobility, etc. The recent success of deep learning methods has revolutionized the field of computer vision, making new developments increasingly closer to deployment that benefits end users.
Overview
Syllabus
Course Introduction.
History.
Image Formation.
Image Representation.
Linear Filtering.
Image in Frequency Domain.
Image Sampling.
Edge Detection.
From Edges to Blobs and Corners.
Scale Space, Image Pyramids and Filter Banks.
Feature Detectors : SIFT and Variants.
Image Segmentation.
Other Feature Spaces.
Human Visual System.
Feature Matching.
Hough Transform.
From Points to Images:Bag-of-Words and VLAD Representations.
Image Descriptor Matching.
Pyramid Matching.
From Traditional Vision to Deep Learning.
Neural Networks: A Review - Part 1.
Neural Networks: A Review - Part 2.
Feedforward Neural Networks and Backpropagation - Part 1.
Feedforward Neural Networks and Backpropagation - Part 2.
Gradient Descent and Variants - Part 1.
Gradient Descent and Variants - Part 2.
Regularization in Neural Networks - Part 1.
Regularization in Neural Networks - Part 2.
Improving Training of Neural Networks - Part 1.
Improving Training of Neural Networks - Part 2.
Convolutional Neural Networks: An Introduction - Part 01.
Convolutional Neural Networks: An Introduction - Part 02.
Backpropagation in CNNs.
Evolution of CNN Architectures for Image Classification-Part 01.
Evolution of CNN Architectures for Image Classification-Part 02.
Recent CNN Architectures.
Finetuning in CNNs.
Explaining CNNs: Visualization Methods.
Explaining CNNs: Early Methods.
Explaining CNNs: Class Attribution Map Methods.
Explaining CNNs: Recent Methods - Part 01.
Explaining CNNs: Recent Methods -Part 02.
Going Beyond Explaining CNNs.
CNNs for Object Detection I PART 01.
CNNs for Object Detection I PART 02.
CNNs for Object Detection II.
CNNs for Segmentation.
CNNs for Human Understanding Faces- Part 01.
CNNs for Human Understanding Faces PART 02.
CNNs for Human Understanding Human Pose and Crowd.
CNNs for Other Image Tasks.
Recurrent Neural Networks Introduction.
Backpropagation in RNNs.
LSTMs and GRUs.
Video Understanding using CNNs and RNNs.
Attention in Vision Models: An Introduction.
Vision and Language: Image Captioning.
Beyond Captioning: Visual QA, Visual Dialog.
Other Attention Models.
Self-Attention and Transformers.
Deep Generative Models: An Introduction.
Generative Adversarial Networks-Part 01.
Generative Adversarial Networks-Part 02.
Variational Autoencoders.
Combining VAEs and GANs.
Beyond VAEs and GANs: Other Deep Generative Models-01.
Beyond VAEs and GANs: Other Deep Generative Models-02.
GAN Improvements.
Deep Generative Models across Multiple Domains.
VAEs and DIsentanglement.
Deep Generative Models: Image Applications.
Deep Generative Models: Video Applications.
Few-shot and Zero-shot Learning - Part 01.
Few-shot and Zero-shot Learning - Part 02.
Self-Supervised Learning.
Adversarial Robustness.
Pruning and Model Compression.
Neural Architecture Search.
Course Conclusion.
Taught by
NPTEL-NOC IITM
