Google & DeepMind Unify Normalization and Activation Layers, Discover ‘EvoNorms’
Researchers unify DNN normalization layers and activation functions into a single computation graph.
Tag: Research
Creating ‘Yuru-Chara’ and a New Class Conditional GAN Approach For Small Datasets
Researchers have proposed a new and inexpensive method for automatically generating yuru-chara characters.
Deflecting Adversarial Attacks
Researchers introduce the notion of deflecting adversarial attacks, which presents a step towards ending the battle between attacks and defenses.
OpenAI Puts CV Models Under Their Microscope
Just as biologists gain insights into organisms by putting model specimens under their microscopes, AI Microscope was designed to help researchers analyze the features that form inside leading CV models.
CMU, DeepMind & Google’s XTREME Benchmarks Multilingual Model Generalization Across 40 Languages
XTREME, a multi-task benchmark that evaluates cross-lingual generalization capabilities of multilingual representations across 40 languages and nine tasks.
Hi-Res Image-To-Image Daytime Translation Without Labels
In a bid to generate high-resolution images showing realistic daytime changes while keeping accurate scene semantics, researchers have proposed a novel image-to-image translation model, HiDT (High Resolution Daytime Translation).
Facebook AI RegNet Models Outperform EfficientNet Models, Run 5x Faster on GPUs
Researchers from Facebook AI introduce a novel low-dimensional design space, RegNet, which produces simple, fast and versatile networks.
Covid-Sanity Interface Elegantly and Efficiently Organizes Web COVID-19 Papers
Covid-Sanity, a web interface designed to navigate the flood of bioRxiv and medRxiv COVID-19 papers and make the research within more searchable and sortable.
Westlake University Researchers Show How SARS-CoV-2 Binds to Human Cells
Respected journal Science Magazine has published COVID-19 research that identifies the viral entry attachment stage for the new coronavirus.
UN, WHO & Mila Map the AI vs COVID-19 Battlefield
Researchers looks at current studies that are using AI to tackle the COVID-19 crisis and suggests some promising future research directions.
AI Deciphers Persian Cuneiform Tablets from 25 Centuries Ago
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.
Novel Hybrid Continual Learning Algorithm Counters Agent Forgetfulness
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
New Compression Method Enables Conditional GANs on Edge Devices
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.
Google Introduces Neuroevolution for Self-Interpretable Agents
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.
Impact of ImageNet Model Selection on Domain Adaptation
Researchers investigate how different ImageNet models affect transfer accuracy on domain adaptation problems.
AI CT Scan Analysis for COVID-19 Detection and Patient Monitoring
A research team has proposed non-contrast thoracic chest CT scans as an effective tool for detecting, quantifying, and tracking COVID-19.
‘Semantic Generation Pyramid’ for Image Generation and Manipulation
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.
BERTLang Helps Researchers Choose Between BERT Models
Researchers from Bocconi University have prepared an online overview of the commonalities and differences between language-specific BERT models and mBERT.
Beyond Lipreading: Visual Speech Recognition Looks You in the Eye
A new study suggests that VSR models could perform even better if they used additional available visual information.
Chinese Researchers Use CNNs to Classify 3000-Year-Old Oracle Bone Scripts
The earliest evidence of China’s recorded history is found in the Shang dynasty (~1600 to 1046 BC), and this hasContinue Reading
Synthesized Paired Data Boosts Facial Manipulation
The model outperforms existing methods in image manipulation and offers researchers a possible solution to the scarcity of paired datasets.
Augmented Training Scheme Fixes CNN Texture Bias
Researchers proposed a new training scheme that targets this bias by controlling and exposing textural information slowly through the training process.
‘Train Large, Then Compress’ – UC Berkeley BAIR Improves Large Transformer Model Training and Inference
Researchers from the Berkeley Artificial Intelligence Research (BAIR) Lab at UC Berkeley explored the effect of Transformer model size on training and inference efficiency.
AutoCompress: SOTA Automatic DNN Pruning for Ultra-High Compression Rates
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.
AI-Based Drug Discovery Pipeline Generates Novel Drug Compounds against Coronavirus
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.
Yoshua Bengio and Team Introduce GNN Benchmarking Framework
Researchers propose a flexible GNN benchmarking framework that can also accommodate the needs of researchers to add new datasets and models.
CookGAN Generates Realistic Meal Images From an Ingredients List
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.
CVPR 2020 Proceeding as Planned; Record 1470 Papers Accepted
The paper acceptance rate fell to approximately 22 percent from 25 percent in 2019 and 29.6 percent in 2018.
BERT-of-Theseus: Compressing BERT by Progressive Module Replacing
Researchers propose a novel model compression approach to effectively compress BERT by progressive module replacing.
Leap in Second-Order Optimization: Shampoo Runtime Boosted 40%
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.
Retrieving Reasoning Paths for Answering Complex Questions
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.
Self-Adversarial Learning with Comparative Discrimination for Text Generation
Researchers have proposed a novel self-adversarial learning (SAL) paradigm for improving GANs’ performance in text generation.
A look at The Case for Bayesian Deep Learning
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?
Introduction to Deep Learning for Graphs and Where It May Be Heading
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.
Geoffrey Hinton & Google Brain Unsupervised Learning Algorithm Improves SOTA Accuracy on ImageNet by 7%
Researchers have proposed a simple but powerful “SimCLR” framework for contrastive learning of visual representations.
Up Close and Personal With BERT – Google’s Epoch-Making Language Model
A recent Google Brain paper looks into Google’s hugely successful transformer network — BERT — and how it represents linguistic information internally.
‘ClearGrasp’ Helps Robots See and Grasp Transparent Objects
Google teamed up with researchers from Synthesis AI and Columbia University to introduce a deep learning approach called ClearGrasp as a first step to teaching machines how to “see” transparent materials.
Google Brain & CMU Semi-Supervised ‘Noisy Student’ Achieves 88.4% Top-1 Accuracy on ImageNet
Researchers from Google Brain and Carnegie Mellon University have released models trained with a semi-supervised learning method called “Noisy Student” that achieve 88.4 percent top-1 accuracy on ImageNet.
17 Billion Parameters! Microsoft DeepSpeed Breeds World’s Largest NLP Model
Deep learning models are getting larger and larger to meet the demand for better and better performance. Meanwhile, the timeContinue Reading
Beyond SPADE: Introducing Semantic Region-Adaptive Normalization for Image Synthesis
Researchers introduced semantic region-adaptive normalization (SEAN), a simple but effective building block for conditional Generative Adversarial Networks (cGAN).