Google’s New “Context R-CNN” Uses Past Images to Improve Detection

2 July 2020

Google’s New “Context R-CNN” Uses Past Images to Improve Detection

Researchers from Google AI have presented an interesting novel method for object detection that takes into account the image context for improving detection performance. As part of a large project…

NVIDIA Released State-of-the-art StyleGAN2 Model

26 June 2020

NVIDIA Released State-of-the-art StyleGAN2 Model

NVIDIA researchers have presented their new project StyleGAN2 at this year’s CVPR 2020. The novel method behind StyleGAN2 is based on previous advancements in generative modeling and the wide known…

Facebook AI Released PointRend: Image Segmentation as Rendering

23 June 2020

Facebook AI Released PointRend: Image Segmentation as Rendering

Researchers from Facebook AI have presented a novel image segmentation method that can produce high-quality, precise segmentation masks. The method is based on a new neural network module called PointRend,…

PULSE: New Deep Network Learns How to Upscale Low-resolution Images

19 June 2020

PULSE: New Deep Network Learns How to Upscale Low-resolution Images

A group of researchers from Duke University has proposed a novel state-of-the-art method for image super-resolution that is able to generate realistic very high-resolution images from a low-resolution input image.…

Facebook’s TransCoder AI Translates Code Between C++, Java and Python

16 June 2020

Facebook’s TransCoder AI Translates Code Between C++, Java and Python

Researchers from Facebook AI have developed a neural network model that can translate code from one programming language to another. Their proposed model, called TransCoder is able to translate between…

AutoSweep: Deep Neural Network Recovers 3D Editable Objects from Single Image

7 June 2020

AutoSweep: Deep Neural Network Recovers 3D Editable Objects from Single Image

A group of researchers from the Shangai Tech University, University of Leeds, and Zhegjiang University have developed a deep neural network for recovering 3D editable objects from a single image.…

f-BRS: New State-of-the-art Model for Interactive Segmentation

5 June 2020

f-BRS: New State-of-the-art Model for Interactive Segmentation

In a novel paper published on this year’s CVPR2020, researchers from the Samsung AI Center in Moscow led by Konstantin Sofiiuk, describe their new method for interactive segmentation named f-BRS.…

Point2Mesh: Deep Neural Network Reconstructs Complex Shape Meshes

5 June 2020

Point2Mesh: Deep Neural Network Reconstructs Complex Shape Meshes

A group of researchers from Tel Aviv University has developed a deep neural network model that reconstructs surface meshes directly from a given input point cloud. In their recent paper,…

Facebook AI Open-sourced DEtection TRansformer Model (DETR)

1 June 2020

Facebook AI Open-sourced DEtection TRansformer Model (DETR)

Facebook AI has announced that they have developed a new approach to object detection called DETR which relies on Transformers to provide end-to-end object detection which matches the performance of…

NVIDIA’s AI Model Re-created the PAC-MAN Game

29 May 2020

NVIDIA’s AI Model Re-created the PAC-MAN Game

NVIDIA has created a fully functional version of the popular PAC-MAN game using deep neural networks without using a game engine. Researchers from NVIDIA have presented the new and powerful…

U² Net (U-Squared Net): A New Neural Network For Salient Object Detection

27 May 2020

U² Net (U-Squared Net): A New Neural Network For Salient Object Detection

A group of researchers from the University of Alberta has proposed new neural network architecture for salient object detection called U² Net. In their recent paper, researchers argue that most…

EfficientPS: New State-of-the-art Model in Panoptic Segmentation

22 May 2020

EfficientPS: New State-of-the-art Model in Panoptic Segmentation

In a recent paper, researchers from the University of Freiburg, Germany, have proposed a new state-of-the-art CNN model for panoptic segmentation which also outperforms all existing models in terms of…

Meta Dataset: Google Released A “Dataset of Datasets” for Few-shot Learning

15 May 2020

Meta Dataset: Google Released A “Dataset of Datasets” for Few-shot Learning

Researchers from Google AI have developed and released a new dataset for few-shot learning called Meta Dataset. The novel dataset is in fact attributed as a “dataset of datasets” and…

Deep Neural Network Predicts Segmentation Mask In Bird-eye View

15 May 2020

Deep Neural Network Predicts Segmentation Mask In Bird-eye View

A group of researchers from the RWTH Aachen University has proposed a deep learning based method for transforming on-road images to semantically segmented bird-eye view (BEV) image. Semantic segmentation has…

Facebook AI Announced a New Challenge on Detecting Hateful Memes

15 May 2020

Facebook AI Announced a New Challenge on Detecting Hateful Memes

Facebook AI has announced the release of a new challenge and dataset called “Hateful Memes”. In their blog post, researchers from Facebook describe the new challenge as another one in…

Researchers Processed Over 16 Million Newspaper Pages to Create Large-scale Newspaper Dataset

12 May 2020

Researchers Processed Over 16 Million Newspaper Pages to Create Large-scale Newspaper Dataset

A group of researchers from the American Library of Congress has joined forces to create a large-scale dataset from newspaper content by analyzing over 16 million historic newspaper pages. As…

CascadePSP: Precise High-resolution Semantic Segmentation Model

10 May 2020

CascadePSP: Precise High-resolution Semantic Segmentation Model

A group of researchers from the Hong Kong University of Science and Technology and Tencent have proposed a new segmentation model that provides high-resolution semantic segmentation without the need of…

Amazon Scientists Published Free Interactive Book on Deep Learning

10 May 2020

Amazon Scientists Published Free Interactive Book on Deep Learning

A group of scientists from Amazon has published a new book on deep learning that is supposed to help students and developers learn about machine learning and deployment of machine…

Mapillary Released The World’s Largest Open Dataset for Places

7 May 2020

Mapillary Released The World’s Largest Open Dataset for Places

Mapillary has released the world’s largest and most diverse open dataset for places recognition, that contains more than 1.6 million images. The new dataset, collected by researchers from Mapillary features…

OpenAI’s Jukebox Neural Network Is Able To Generate Realistic Music

3 May 2020

OpenAI’s Jukebox Neural Network Is Able To Generate Realistic Music

OpenAI announced the release of Jukebox – a new neural network model that is able to generate realistic music of a wide variety of genres and styles. Automatic music generation…

Deep Neural Network Analyzes Table Tennis Videos And Acts as a Referee

3 May 2020

Deep Neural Network Analyzes Table Tennis Videos And Acts as a Referee

A group of researchers from OSAI (Constanta) has designed a deep neural network for real-time analysis of table-tennis videos. Their model, named TTNet is able to extract temporal and spatial…