IIT Hyderabad · Computer Science

Deep Learning for Computer Vision

Prof. Vineeth N Balasubramanian · 2023 · 64 free video lectures

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…

▶ Play on Open Lecture HallCourse page ↗

Lectures

  1. Course Introduction
  2. History
  3. [Optional] Image Formation
  4. Image Representation
  5. Linear Filtering
  6. Image in Frequency Domain
  7. [Optional] Image Sampling
  8. Edge Detection
  9. From Edges to Blobs and Corners
  10. Scale Space, Image Pyramids and Filter Banks
  11. Feature Detectors : SIFT and Variants
  12. [Optional] Image Segmentation
  13. Other Feature Spaces
  14. [Optional] Human Visual System
  15. Neural Networks: A Review - Part 1
  16. Neural Networks: A Review - Part 2
  17. Feedforward Neural Networks and Backpropagation - Part 1
  18. Feedforward Neural Networks and Backpropagation - Part 2
  19. Gradient Descent and Variants - Part 1
  20. Gradient Descent and Variants - Part 2
  21. Regularization in Neural Networks - Part 1
  22. Regularization in Neural Networks - Part 2
  23. Improving Training of Neural Networks - Part 1
  24. Improving Training of Neural Networks - Part 2
  25. Convolutional Neural Networks: An Introduction - Part 01
  26. Convolutional Neural Networks: An Introduction - Part 02
  27. Backpropagation in CNNs
  28. CNN Architectures for Image Classification: AlexNet, VGG
  29. Evolution of CNN Architectures: InceptionNet, ResNet
  30. Newer and Recent CNN Architectures
  31. Finetuning CNNs
  32. Visualizing CNNs
  33. CNNs for Object Detection: Pre-Deep Learning Era and Initial Steps
  34. CNNs for Object Detection: Two-Stage Models
  35. CNNs for Object Detection: Single-stage Models
  36. CNNs for Segmentation
  37. Recurrent Neural Networks: Introduction
  38. Backpropagation in RNNs
  39. LSTMs and GRUs
  40. Video Understanding using CNNs and RNNs
  41. Attention in Vision Models: An Introduction
  42. Soft and Hard Attention: Image Captioning
  43. Additional Content: Beyond Captioning: Visual QA and Dialog
  44. Self-Attention and Transformers
  45. From Transformers to Vision Transformers
  46. Transformers for Detection
  47. Transformers for Segmentation
  48. Deep Generative Models: An Introduction
  49. Generative Adversarial Networks - Part 1
  50. Generative Adversarial Networks - Part 2
  51. GAN Hacks and Improvements
  52. Variational Autoencoders
  53. VAEs and Disentanglement
  54. Introduction to Diffusion Models and DDPMs - Part 1
  55. Introduction to Diffusion Models and DDPMs - Part 2
  56. Classifier and Classifier-Free Diffusion Guidance
  57. Contrastive Learning and History in Face Understanding - Part 1
  58. Contrastive Learning and History in Face Understanding - Part 2
  59. Self-Supervised Learning: SimCLR
  60. Vision Language Models: Introduction and History
  61. CLIP: The Anchoring Inflection Point
  62. Beyond CLIP: BLIP, BLIP-2 and CoCA
  63. From VLMs to Multimodal LLMs
  64. Course Conclusion

From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IIT Hyderabad.

Open Lecture Hall is free, with no ads and no sign-up. It is not run by or connected to any university; the lectures are the universities' own free recordings, played from where they host them. About & rights