AI Technology & Industry Review
Technical review of the newest machine intelligence research.
Their proposed framework outperforms state-of-the-art approaches for 3D reconstructions from 2D and 2.5D data, achieving 12 percent better performance on average in the ShapeNet benchmark dataset and up to 19 percent for certain classes of objects.
Researchers from the University of Chicago Oriental Institute (OI) and the Department of Computer Science have introduced an artificial intelligence tool called DeepScribe designed to read cuneiform tablets from 25 centuries ago.
Researchers have introduced a novel hybrid continual learning algorithm, Adversarial Continual Learning, which aims to enable the persistent explicit or implicit replay of experiences by storing original samples
A research team from MIT, Adobe Research, and Shanghai Jiao Tong University have introduced a novel method for reducing the cost and size of Conditional GAN generators.
Researchers from Google Brain Tokyo and Google Japan have proposed a novel approach that helps guide reinforcement learning (RL) agents to what’s important in vision-based tasks.
Researchers investigate how different ImageNet models affect transfer accuracy on domain adaptation problems.
Google Brain announced this week that it is open-sourcing its object detector EfficientDet, which achieves SOTA performance while requiring significantly less compute.
The new goal of the Folding@home project is modelling the structure of SARS-CoV-2 spike protein to identify sites that can be targeted by a therapeutic antibody.
A research team has proposed non-contrast thoracic chest CT scans as an effective tool for detecting, quantifying, and tracking COVID-19.
Researchers have proposed a new image generative model that leverages the hierarchical space of deep features learned by pretrained classification networks and provides a unified and versatile framework for image generation and manipulation tasks.
Researchers from Bocconi University have prepared an online overview of the commonalities and differences between language-specific BERT models and mBERT.
A new study suggests that VSR models could perform even better if they used additional available visual information.
The earliest evidence of China’s recorded history is found in the Shang dynasty (~1600 to 1046 BC), and this hasContinue Reading
The model outperforms existing methods in image manipulation and offers researchers a possible solution to the scarcity of paired datasets.
Organizers announced today that the COVID-19 outbreak and associated travel restrictions have forced the cancellation of the “physical conference” ofContinue Reading
Researchers proposed a new training scheme that targets this bias by controlling and exposing textural information slowly through the training process.
Researchers from the Berkeley Artificial Intelligence Research (BAIR) Lab at UC Berkeley explored the effect of Transformer model size on training and inference efficiency.
Researchers proposed an automatic structured pruning framework, AutoCompress, which adopts the 2018 ADMM-based weight pruning algorithm and outperforms previous automatic model compression methods while maintaining high accuracy.
DeepMind released the structure predictions for six proteins associated with SARS-CoV-2, the virus that causes COVID-19, using the most up-to-date version of their AlphaFold system.
A new study leverages an established AI-based drug discovery pipeline to produce molecular structures as part of the widening fight against the 2019-nCoV outbreak.
Researchers propose a flexible GNN benchmarking framework that can also accommodate the needs of researchers to add new datasets and models.
UC Berkeley and Adobe Research have introduced a “universal” detector that can distinguish real images from generated images regardless of what architectures and/or datasets were used for training.
Proposed by researchers from the Rutgers University and Samsung AI Center in the UK, CookGAN uses an attention-based ingredients-image association model to condition a generative neural network tasked with synthesizing meal images.
The KaoKore dataset includes 5552 RGB image files drawn from the 2018 Collection of Facial Expressions dataset of cropped face images from Japanese artworks.
Researchers propose a novel model compression approach to effectively compress BERT by progressive module replacing.
The crowdsourcing produced 111.25 hours of video from 54 non-expert demonstrators to build “one of the largest, richest, and most diverse robot manipulation datasets ever collected using human creativity and dexterity.”
A Google-led research team has introduced a new method for optimizing neural network parameters that is faster than all common first-order methods on complex problems.
Fast and accurate diagnosis is critical on the front line, and now an AI-powered diagnostic assessment system is helping Hubei medical teams do just that.
In an attempt to equip the TF-IDF-based retriever with a state-of-the-art neural reading comprehension model, researchers introduced a new graph-based recurrent retrieval approach.
The proposed system is capable of searching the continental United States at 1 -meter pixel resolution, corresponding to approximately 2 billion images, in around 0.1 seconds.
MonoLayout, a practical deep neural architecture that takes just a single image of a road scene as input and outputs an amodal scene layout in bird’s-eye view.
In a bid to raise awareness of the threats posed by climate change, the Mila team recently published a paper that uses GANs to generate images of how climate events may impact our environments — with a particular focus on floods.
Synced Global AI Weekly February 23rd
Bayesian inference meanwhile leverages Bayes’ theorem to update the probability of a hypothesis as additional data becomes available. How can Bayesian inference benefit deep learning models?
DeepMind announced yesterday the release of Haiku and RLax — new JAX libraries designed for neural networks and reinforcement learning respectively.
Researchers from Italy’s University of Pisa present a clear and engaging tutorial on the main concepts and building blocks involved in neural architectures for graphs.
Researchers have proposed a novel generator network specialized on the illustrations in children’s books.
Researchers have proposed a simple but powerful “SimCLR” framework for contrastive learning of visual representations.
A recent Google Brain paper looks into Google’s hugely successful transformer network — BERT — and how it represents linguistic information internally.
The tool enables researchers to try, compare, and evaluate models to decide which work best on their datasets or for their research purposes.