NPTEL : NOC:Deep Learning for Computer Vision (Computer Science and Engineering)

Co-ordinators : Prof. Vineeth N Balasubramanian


Lecture 1 - Course Introduction

Lecture 2 - History

Lecture 3 - Image Formation

Lecture 4 - Image Representation

Lecture 5 - Linear Filtering

Lecture 6 - Image in Frequency Domain

Lecture 7 - Image Sampling

Lecture 8 - Edge Detection

Lecture 9 - From Edges to Blobs and Corners

Lecture 10 - Scale Space, Image Pyramids and Filter Banks

Lecture 11 - Feature Detectors: SIFT and Variants

Lecture 12 - Image Segmentation

Lecture 13 - Other Feature Spaces

Lecture 14 - Human Visual System

Lecture 15 - Feature Matching

Lecture 16 - Hough Transform

Lecture 17 - From Points to Images: Bag-of-Words and VLAD Representations

Lecture 18 - Image Descriptor Matching

Lecture 19 - Pyramid Matching

Lecture 20 - From Traditional Vision to Deep Learning

Lecture 21 - Neural Networks: A Review - Part 1

Lecture 22 - Neural Networks: A Review - Part 2

Lecture 23 - Feedforward Neural Networks and Backpropagation - Part 1

Lecture 24 - Feedforward Neural Networks and Backpropagation - Part 2

Lecture 25 - Gradient Descent and Variants - Part 1

Lecture 26 - Gradient Descent and Variants - Part 2

Lecture 27 - Regularization in Neural Networks - Part 1

Lecture 28 - Regularization in Neural Networks - Part 2

Lecture 29 - Improving Training of Neural Networks - Part 1

Lecture 30 - Improving Training of Neural Networks - Part 2

Lecture 31 - Convolutional Neural Networks: An Introduction - Part 1

Lecture 32 - Convolutional Neural Networks: An Introduction - Part 2

Lecture 33 - Backpropagation in CNNs

Lecture 34 - Evolution of CNN Architectures for Image Classification - Part 1

Lecture 35 - Evolution of CNN Architectures for Image Classification - Part 2

Lecture 36 - Recent CNN Architectures

Lecture 37 - Finetuning in CNNs

Lecture 38 - Explaining CNNs: Visualization Methods

Lecture 39 - Explaining CNNs: Early Methods

Lecture 40 - Explaining CNNs: Class Attribution Map Methods

Lecture 41 - Explaining CNNs: Recent Methods - Part 1

Lecture 42 - Explaining CNNs: Recent Methods - Part 2

Lecture 43 - Going Beyond Explaining CNNs

Lecture 44 - CNNs for Object Detection-I - Part 1

Lecture 45 - CNNs for Object Detection-I - Part 2

Lecture 46 - CNNs for Object Detection-II

Lecture 47 - CNNs for Segmentation

Lecture 48 - CNNs for Human Understanding: Faces - Part 1

Lecture 49 - CNNs for Human Understanding: Faces - Part 2

Lecture 50 - CNNs for Human Understanding: Human Pose and Crowd

Lecture 51 - CNNs for Other Image Tasks

Lecture 52 - Recurrent Neural Networks: Introduction

Lecture 53 - Backpropagation in RNNs

Lecture 54 - LSTMs and GRUs

Lecture 55 - Video Understanding using CNNs and RNNs

Lecture 56 - Attention in Vision Models: An Introduction

Lecture 57 - Vision and Language: Image Captioning

Lecture 58 - Beyond Captioning: Visual QA, Visual Dialog

Lecture 59 - Other Attention Models

Lecture 60 - Self-Attention and Transformers

Lecture 61 - Deep Generative Models: An Introduction

Lecture 62 - Generative Adversarial Networks - Part 1

Lecture 63 - Generative Adversarial Networks - Part 2

Lecture 64 - Variational Autoencoders

Lecture 65 - Combining VAEs and GANs

Lecture 66 - Beyond VAEs and GANs: Other Deep Generative Models - Part 1

Lecture 67 - Beyond VAEs and GANs: Other Deep Generative Models - Part 2

Lecture 68 - GAN Improvements

Lecture 69 - Deep Generative Models across Multiple Domains

Lecture 70 - VAEs and DIsentanglement

Lecture 71 - Deep Generative Models: Image Applications

Lecture 72 - Deep Generative Models: Video Applications

Lecture 73 - Few-shot and Zero-shot Learning - Part 1

Lecture 74 - Few-shot and Zero-shot Learning - Part 2

Lecture 75 - Self-Supervised Learning

Lecture 76 - Adversarial Robustness

Lecture 77 - Pruning and Model Compression

Lecture 78 - Neural Architecture Search

Lecture 79 - Course Conclusion