Rigging the Lottery: New Method for Training Sparse Deep Networks

18 September 2020

Rigging the Lottery: New Method for Training Sparse Deep Networks

Researchers from Google AI have proposed a new way of training sparse neural networks that overcomes the typical issues found in existing dense-to-sparse methods. Past research has shown that deep…

Researchers From Google Proposed a New Imitation Learning Method

17 September 2020

Researchers From Google Proposed a New Imitation Learning Method

A group of researchers from Google AI has developed a new imitation learning method called Primal Wasserstein Imitation Learning (PWIL). The newly proposed method for imitation learning does not rely…

UI Meets AI: FEELER Helps Designers Find the Best UI Solution

13 September 2020

UI Meets AI: FEELER Helps Designers Find the Best UI Solution

Researchers from Baidu in a collaboration with several universities and research institutes have developed an intelligent framework for the exploration of UI design solutions using collective machine learning. The new…

Product-10K: New Large-scale Dataset of Product Images

10 September 2020

Product-10K: New Large-scale Dataset of Product Images

A new, large-scale product image dataset was recently published by researchers from JD AI Research. Motivated by the lack of precise and large-scale datasets of product images, researchers have started…

Neural Network Generates Speech Gestures According to Speech

10 September 2020

Neural Network Generates Speech Gestures According to Speech

A group of researchers from the University of Science and Technology, ETRI from Korea have developed a method for learning speech gesture generation using online speech videos. In their latest…

Researchers Have Developed A Road Damage Detection Model for Multiple Countries

6 September 2020

Researchers Have Developed A Road Damage Detection Model for Multiple Countries

A group of researchers from several research institutes and universities has collaborated together on a project to develop a road damage detection model that works well in multiple countries. Considering…

Wav2Lip: Neural Network Successfully Syncs Lips with Speech

4 September 2020

Wav2Lip: Neural Network Successfully Syncs Lips with Speech

A group of researchers has developed and released a novel deep neural network that can convert a video and audio signal into a lip-synced video. In their recent paper, the…

Axial-DeepLab: New State-of-the-art Panoptic Segmentation Network

30 August 2020

Axial-DeepLab: New State-of-the-art Panoptic Segmentation Network

In their recent paper, researchers from Google AI have proposed a new state-of-the-art model for panoptic and semantic segmentation. The new model comes as an improvement over the series of…

Researchers Used Machine Learning to Increase Coverage in Colonoscopy Screenings

30 August 2020

Researchers Used Machine Learning to Increase Coverage in Colonoscopy Screenings

In another research project from Google AI, researchers have developed a machine learning method that helps doctors increase coverage in colonoscopy screenings. Colonoscopy as a procedure for detecting polyps and…

TensorFlow Coder: New Tool Helps You Write TensorFlow Code

28 August 2020

TensorFlow Coder: New Tool Helps You Write TensorFlow Code

Researchers from Google have developed and released a new tool that helps developers to easily write TensorFlow code. Basically, the new tool called TensorFlow Coder which is part of Tensorflow…

MIT Researchers Explore What Makes Deepfakes Detectable

27 August 2020

MIT Researchers Explore What Makes Deepfakes Detectable

Researchers from MIT University have conducted a research project where their goal was to understand what makes deepfakes detectable. With the numerous advances in image generation in the past decade,…

Neural Network Infers 3D Human-Object Interactions

25 August 2020

Neural Network Infers 3D Human-Object Interactions

Researchers from the Carnegie Mellon University, Facebook AI Research, Argo AI, and the University of California have developed a method that successfully extracts 3D humans and objects along with their…

WebDataset: A New Python Library For Dealing with Large Datasets

23 August 2020

WebDataset: A New Python Library For Dealing with Large Datasets

WebDataset is a novel Python library that allows efficient data access and overcomes most challenges introduced by working with very large datasets. The library was developed in order to overcome…

Researchers Use AI To Speed up MRI Scanning Procedure

20 August 2020

Researchers Use AI To Speed up MRI Scanning Procedure

In a 2-year-old collaboration project, researchers from Facebook AI and New York University Langone Health, have developed a new way to accelerate MRI scanning procedures by leveraging AI technologies. The…

LogoDet-3K: Researchers Collected a Large-Scale Logo Detection Dataset

16 August 2020

LogoDet-3K: Researchers Collected a Large-Scale Logo Detection Dataset

Researchers from Shandong Normal University and the Chinese Academy of Sciences have collected and published a large-scale logo detection dataset. In the context of branding and brand management, logo detection…

Image-2-Lixel: New Method For Accurate Human Pose and Mesh Estimation

12 August 2020

Image-2-Lixel: New Method For Accurate Human Pose and Mesh Estimation

In a novel paper, researchers from the Seoul National University in Korea have proposed an accurate method for 3D human pose and mesh estimation from a single image. Typically human…

New Method Learns To Generate Stereo Image Pairs from Single Image

8 August 2020

New Method Learns To Generate Stereo Image Pairs from Single Image

A group of researchers from Niantic, the University of Edinburgh and UCL has developed an interesting method that learns to generate stereo images from a single monocular image. In their…

SipMask: New State-of-the-art Instance Segmentation Model

3 August 2020

SipMask: New State-of-the-art Instance Segmentation Model

A group of researchers has proposed a new instance segmentation method that achieves state-of-the-art performance on several popular benchmark datasets. Researchers’ main contribution is a novel spatial preservation module (SP)…

CelebA-Spoof: New Large-Scale Face Anti-Spoofing Dataset

28 July 2020

CelebA-Spoof: New Large-Scale Face Anti-Spoofing Dataset

A group of researchers has collected and released a novel anti-spoofing dataset built on top of the popular CelebA dataset. The novel dataset, named CelebA-Spoof is a large scale dataset…

Voila Lets You Create a Standalone App From Your Jupyter Notebook

24 July 2020

Voila Lets You Create a Standalone App From Your Jupyter Notebook

Voila is a new Python package and a recent addition to the Jupyter Notebook ecosystem, which can turn any Jupyter notebook into a standalone web application or a dashboard. A…

Semantic Data Augmentation Improves Neural Network’s Generalization

24 July 2020

Semantic Data Augmentation Improves Neural Network’s Generalization

A group of researchers from the University of Beijing has proposed a novel implicit semantic data augmentation method that improves the generalization capabilities of deep neural networks. Data augmentation has…