Skip to main content
Back to top
Ctrl
+
K
Search
Ctrl
+
K
Search
Ctrl
+
K
Deep Learning for Computer Vision
Search
Ctrl
+
K
Week 1: Image Formation and Representation
Week 1, Lecture 1: Course Introduction and Overview
Week 1, Lecture 2: History
Week 1, Lecture 3: Image Formation
Week 1, Lecture 4: Image Representation
Week 1, Lecture 5: Linear Filtering, Correlation and Convolution
Week 1, Lecture 6: Image in the Frequency Domain
Week 1, Lecture 7: Image Sampling and Interpolation
Week 2: Feature Detection and Description
Week 2, Lecture 1: Edge Detection
Week 2, Lecture 2: From Edges to Blobs and Corners
Week 2, Lecture 3: Scale Space, Image Pyramids and Filter Banks
Week 2, Lecture 4: SIFT and Variants
Week 2, Lecture 5: Image Segmentation
Week 2, Lecture 6: Other Feature Spaces
Week 2, Lecture 7: Human Visual System
Week 3: Neural Networks
Week 3, Lecture 1: The McCulloch-Pitts Neuron and the Perceptron
Week 3, Lecture 2: The XOR Conundrum, MLPs, and Activation Functions
Week 3, Lecture 3: Feedforward Networks and Gradient Descent
Week 3, Lecture 4: Backpropagation, Built by Hand and Verified
Week 3, Lecture 5: Momentum and Nesterov Accelerated Gradient
Week 3, Lecture 6: SGD and Adaptive Optimizers, Built From Scratch
Week 3, Lecture 7: Regularization and L2 Weight Decay
Week 3, Lecture 8: Early Stopping, Data Augmentation, Noise, Ensembles, and Dropout
Week 3, Lecture 9: Activation Functions In Depth
Week 3, Lecture 10: Weight Initialization and Batch Normalization
Week 4: Convolutional Neural Networks
Week 4, Lecture 1: The Convolution Operation and Its (Hyper)Parameters
Week 4, Lecture 2: Why CNNs? Local Receptive Fields, Weight Sharing, Pooling, and Convolution Variants
Week 4, Lecture 3: Backpropagation in CNNs
Week 4, Lecture 4: CNN Architectures for Image Classification (LeNet, AlexNet, VGG)
Week 5: CNN Architectures, Finetuning and Visualization
Week 5, Lecture 1: Evolution of CNN Architectures (InceptionNet and ResNet)
Week 5, Lecture 2: More and Recent CNN Architectures
Week 5, Lecture 3: Finetuning CNNs (Transfer Learning)
Week 5, Lecture 4: Visualizing CNNs
Week 6: Object Detection and Segmentation
Week 6, Lecture 1: CNNs for Object Detection (Foundations)
Week 6, Lecture 2: Two-Stage Object Detectors (The R-CNN Family)
Week 6, Lecture 3: CNNs for Object Detection, Single-Stage Methods
Week 6, Lecture 4: CNNs for Segmentation
Week 7: Recurrent Neural Networks
Week 7, Lecture 1: Recurrent Neural Networks: An Introduction
Week 7, Lecture 2: Backpropagation in RNNs
Week 7, Lecture 3: LSTMs and GRUs
Week 7, Lecture 4: Video Understanding using CNNs and RNNs
Week 8: Attention and Transformers
Week 8, Lecture 1: Attention Models in Vision: An Introduction
Week 8, Lecture 2: Soft and Hard Attention: Image Captioning
Week 8, Lecture 3: Beyond Captioning: Visual QA and Visual Dialog
Week 8, Lecture 4: Self-Attention and Transformers
Week 9: Vision Transformers
Week 9, Lecture 1: From Transformers to Vision Transformers
Week 9, Lecture 2: Transformers for Detection
Week 9, Lecture 3: Transformers for Segmentation
Week 10: Deep Generative Models
Week 10, Lecture 1: Deep Generative Models
Week 10, Lecture 2: GAN Part 1
Week 10, Lecture 3: GAN Part 2
Week 10, Lecture 4: GAN Hacks and Improvement
Week 10, Lecture 5: VAE’s
Week 10, Lecture 6: VAE’s and disentanglement
Week 11: Diffusion Models
Week 11, Lecture 1: Diffusion Models and DDPM : Part 1
Week 11, Lecture 2: Diffusion Models and DDPM : Part 2
Week 11, Lecture 3: Classifier and Classifier Free Diffusion Guidance
Week 12: Self-Supervised and Vision-Language Models
Week 12, Lecture 1: Contrastive Learning Part 1
Week 12, Lecture 2: Contrastive Learning Part 2
Week 12, Lecture 3: SSL : SimCLR
Week 12, Lecture 4: VLM : Intro and History
Week 12, Lecture 5: CLIP
Week 12, Lecture 6: Beyond CLIP: BLIP,BLIP-2 and CoCA
Week 12, Lecture 7: From VLM’s to Multimodal LLM’s
Week 12, Lecture 8: Course Conclusion
Index