Facebook to Use AI to Find & Understand Memes

Facebook is going to use machine learning system called Rosetta to deliver a more personalized news feed, as well as tracking spam, offensive or banned content
13 September 2018   882

Facebook introduced Rosetta - machine learning system, which in real time extracts text from more than a billion publicized images and videos in social networks in different languages, and then recognizes their context.

Rosetta performs simultaneously two independent processes: detection of areas that can contain text, and word recognition using the Faster R-CNN convolutional neural network on the ResNet18 architecture.

The algorithm recognizes English, Arabic, Hindi, German, Spanish and other languages, including those that have horizontal right-to-left writing, diacritics and other specific characters.

In the future, the corporation will try to teach the system to recognize more languages, types of text and image templates.

Facebook is going to use Rosetta to deliver a more personalized news feed, as well as tracking spam, offensive or banned content. Now it is sorted by operators and it takes a long time.

In June, 2018, researchers from Stanford talked about a model of machine learning that could create memes in the style of "advising animals." The authors noted that on average, an "artificial" meme is difficult to distinguish from "real" in the context of the quality of the joke in it.

Nvidia to Open SPADE Source Code

SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019   671

NVIDIA has released the source code for the SPADE machine learning system (GauGAN), which allows for the synthesis of realistic landscapes based on rough sketches, as well as training models associated with the project. The system was demonstrated in March at the GTC 2019 conference, but the code was published only yesterday. The developments are open under the non-free license CC BY-NC-SA 4.0 (Creative Commons Attribution-NonCommercial-ShareAlike 4.0), allowing use only for non-commercial purposes. The code is written in Python using the PyTorch framework.

Sketches are drawn up in the form of a segmented map that determines the placement of exemplary objects on the scene. The nature of the generated objects is set using color labels. For example, a blue fill turns into sky, blue into water, dark green into trees, light green into grass, light brown into stones, dark brown into mountains, gray into snow, a brown line into a road, and a blue line into the river. Additionally, based on the choice of reference images, the overall style of the composition and the time of day are determined. The proposed tool for creating virtual worlds can be useful to a wide range of specialists, from architects and urban planners to game developers and landscape designers.

Objects are synthesized by a generative-adversarial neural network (GAN), which, based on a schematic segmented map, creates realistic images by borrowing parts from a model previously trained on several million photographs. In contrast to the previously developed systems of image synthesis, the proposed method is based on the use of adaptive spatial transformation followed by transformation based on machine learning. Processing a segmented map instead of semantic markup allows you to achieve an exact match of the result and control the style.

To achieve realism, two competing neural networks are used: the generator and the discriminator (Discriminator). The generator generates images based on mixing elements of real photos, and the discriminator identifies possible deviations from real images. As a result, a feedback is formed, on the basis of which the generator begins to assemble more and more qualitative samples, until the discriminator ceases to distinguish them from the real ones.