Toggle navigation sidebar
Toggle in-page Table of Contents
Deep Learning For Computer Vision
Welcome to the Course
Prerequisites
Week 1
Lecture 1: Course Introduction
Lecture 2: History
Lecture 3: Image Formation
Lecture 4: Image Representation
Code
Lecture 5: Linear Filtering, Correlation, Convolution
Code
Lecture 6: Image in Frequency Domain
Lecture 7: Image Sampling
Week 2
Lecture 1: Edge Detection
Code
Lecture 2: From Edges to Blobs and Corners
Lecture 3: Scale Space, Image Pyramids and Filter Banks
Code
Lecture 4: SIFT and Variants
Lecture 5: Image Segmentation
Lecture 6: Other Feature Spaces
Lecture 7: Human Visual System
Week 3
Lecture 1: Feature Matching
Code
Lecture 2: Hough Transform
Lecture 3: From Points to Images: Bag-of-Words and VLAD Representations
Lecture 4: Image Descriptor Matching
Lecture 5: Pyramid Matching
Lecture 6: From Traditional Vision to Deep Learning
Week 4
Lecture 1 : Neural Networks: A Review Part 1
Code
Lecture 2: Neural Networks: A Review Part 2
Code
Lecture 3: Feedforward Neural Networks and Backpropagation Part 1
Code
Lecture 4: Feedforward Neural Networks and Backpropagation Part 2
Code
Lecture 5: Gradient Descent and Variants Part 1
Code
Lecture 6: Gradient Descent and Variants Part 2
Code
Lecture 7: Regularization in Neural Networks Part 1
Code
Lecture 8: Regularization in Neural Networks Part 2
Code
Lecture 9: Improving Training of Neural Networks Part 1
Code
Lecture 10: Improving Training of Neural Networks Part 2
Code
Week 5
Lecture 1: Convolutional Neural Networks: An Introduction - Part 01
Lecture 2: Convolutional Neural Networks: An Introduction - Part 02
Lecture 3: Backpropagation in CNNs
Lecture 4: Evolution of CNN Architectures for Image Classification - Part01
Lecture 5: Evolution of CNN Architectures for Image Classification - Part02
Code
Lecture 6: Recent CNN Architectures
Lecture 7: Finetuning in CNNs
Code
Week 6
Lecture 1: Explaining CNNs: Visualization Methods
Lecture 2: Explaining CNNs: Early Methods
Lecture 3: Explaining CNNs: Class Attribution Map Methods
Code
Lecture 4: Explaining CNNs: Recent Methods - Part 01
Lecture 5: Explaining CNNs: Recent Methods - Part 02
Lecture 6: Going Beyond Explaining CNNs
Week 7
Lecture 1: CNNs for Object Detection-I - Part 01
Lecture 2: CNNs for Object Detection-I - Part 02
Lecture 3: CNNs for Object Detection-II
Lecture 4: CNNs for Segmentation
Code
Lecture 5: CNNs for Human Understanding: Faces -Part 01
Lecture 6: CNNs for Human Understanding: Faces -Part 02
Code
Lecture 7: CNNs for Human Understanding: Human Pose and Crowd
Lecture 8: CNNs for Other Image Tasks
Week 8
Lecture 1: Recurrent Neural Networks: Introduction
Code
Lecture 2: Backpropagation in RNNs
Lecture 3: LSTMs and GRUs
Code
Lecture 4: Video Understanding using CNNs and RNNs
Week 9
Lecture 1: Attention in Vision Models: An Introduction
Lecture 2: Vision and Language: Image Captioning
Lecture 3: Beyond Captioning: Visual QA, Visual Dialog
Lecture 4: Other Attention Models
Lecture 5: Self-Attention and Transformers
Week 10
Lecture 10: Deep Generative Models: An Introduction
Lecture 2: Generative Adversarial Networks - Part 1
Lecture 3: Generative Adversarial Networks - Part 2
Lecture 4: Variational Autoencoders
Lecture 5: Combining VAEs and GANs
Lecture 6: Beyond VAEs and GANs: Other Deep Generative Models - Part 1
Lecture 7 : Beyond VAEs and GANs: Other Deep Generative Models - Part 2
Week 11
Lecture 1 : GAN Improvements
Lecture 2: Deep Generative Models across Multiple Domains
Lecture 3: VAEs and Disentanglement
Lecture 4: Deep Generative Models: Image Applications
Lecture 5: Deep Generative Models: Video Applications
Week 12
Lecture 1: Few-shot and Zero-shot Learning - Part 1
Lecture 2: Few-shot and Zero-shot Learning - Part 2
Lecture 3: Self-Supervised Learning
Lecture 4: Adversarial Robustness
Lecture 5: Pruning and Model Compression
Lecture 6: Neural Architecture Search
Lecture 7 : Course Conclusion
repository
open issue
.md
.pdf
Week 9
Week 9
#
