Skip to content

Lecture 2B: Computer Vision

Video

Slides

Download slides as PDF

Notes

Lecture by Sergey Karayev.

In this video, we will review notable applications of deep learning in computer vision. First, we will tour some ConvNet architectures. Then, we will talk about localization, detection, and segmentation problems. We will conclude with more advanced methods.

Learn more at this website: https://paperswithcode.com/area/computer-vision

  • 00:00 - Introduction
  • 02:51 - AlexNet
  • 05:09 - ZFNet
  • 06:54 - VGGNet
  • 09:06 - GoogLeNet
  • 11:57 - ResNet
  • 15:15 - SqueezeNet
  • 17:05 - Architecture Comparisons
  • 20:00 - Localization, Detection, and Segmentation Tasks
  • 24:00 - Overfeat, YOLO, and SSD Methods
  • 28:01 - Region Proposal Methods (R-CNN, Faster R-CNN, Mask R-CNN, U-Net)
  • 34:33 - Advanced Tasks (3D Shape Inference, Face Landmark Recognition, and Pose Estimation)
  • 37:00 - Adversarial Attacks
  • 40:56 - Style Transfer