Make Some Noise for Score Based Models

Blob Pitt's next big blockbuster Generative models have reached a remarkable capacity to synthesize original instances after learning a data distribution. In the arena of image generation, the recent SOTA tracks alongside advances in a family of models called generative adversarial networks or GANs. This framework of jointly training two networks gives rise to a learnable loss. Despite these successes, GANs are challenged by training instabilities. The latest StyleGAN2-ada mitigates mode collapse arising from overfit discriminators using test time data augmentation....

 · 3 min · Terry Rodriguez & Salma Mayorquin

Image Inpainting for Content Localization

In our last post, we trained StyleGAN2 over a corpus of hundreds of thousands theatrical posters we scraped from sites like IMDb. Then we explored image retrieval applications of StyleGAN2 after extracting embeddings by projecting our image corpus onto the learned latent factor space. Image retrieval techniques can form the basis of personalized image recommendations as we use content similarity to generate new recommendations. Netflix engineers posted about testing the impact on user engagement from artwork produced by their content creation team....

 · 3 min · Terry Rodriguez & Salma Mayorquin

Applying GAN Latent Factors for Image Retrieval

GANs consistently achieve state of the art performance in image generation by learning the distribution of an image corpus. The newest models often use explicit mechanisms to learn factored representations for images which can be help provide faceted image retrieval, capable of conditioning output on key attributes. In this post, we explore applying StyleGAN2 embeddings in image retrieval tasks. StyleGAN2 To begin, we train a StyleGAN2 model to generate theatrical posters from our image corpus....

 · 3 min · Terry Rodriguez & Salma Mayorquin

Deepfake Detection With NVIDIA TLT 3.0 and DeepStream SDK

Last year, over 2 thousand teams participated in Kaggle’s Deepfake detection video classification challenge. For this task, contestants were provided 470 GB of high resolution video and required to submit a notebook which predicts whether each sample video file has been deepfaked with a 9 hour run-time limit. Since most deepfake technology performs a faceswap, contestants concentrated around face detection and analysis. Beginning with face detection, contestants could develop an image classifier using the provided labels....

 · 5 min · Terry Rodriguez & Salma Mayorquin

Movie Trailer Similarity for Recommendation

Intro In a previous post, we discussed scraping a movie poster image corpus with genre labels from imdb and learning image similarity models using tensorflow. In this post, we extend this idea to recommend movie trailers based on audio-visual similarity. Data We started by scraping IMDB for movie trailers and their genre tags as labels. Using Scrapy, it is easy to build a text file of video links to then download with youtube-dl....

 · 4 min · Terry Rodriguez & Salma Mayorquin