Applications of Generative Modeling
summary
Covers how generative models (convolutional neural networks and generative adversarial networks) are applied in computer vision for tasks that create images rather than just classify them, specifically demonstrating artistic style transfer, image generation, and image-to-image translation.
AI-written summary · about
chapters (11)
- 0:00Start
- 1:03Speaker intro: Vivek Singhal
- 1:19Generative Adversarial Networks (GANS)
- 8:25Text to Image with StackGAN
- 10:13Faces with GANS
- 12:25Artistic Style Transfer
- 14:15Predicting next
- 14:45Interactive Image Generation
- 16:56Image to Image Translation using Conditional GAN
- 20:34Forging MNIST with Fully Connected GANS
- 24:26Take-Away Messages
related talks
40mOverview of Generative Adversarial Networks (GANs)
47mUnmasking Generative Adversarial Networks
43mHitchhiker’s Guide to Generative Adversarial Networks (GANs)
13m[Interactive] Neural Style Transfer: The Art and Science of Generative AI
30mGenerative AI will enable crowdsourced interactivity
47mTrapping the Accident
37mLearning AI with Van Gogh, Botero and Cruz‑Diez
13mNavigating Generative AI and Its Risks