Microsoft & MIT Apply Adversarially Robust Models for Better Transfer Learning
Despite being less accurate on ImageNet, adversarially robust neural networks can match or improve their standard counterparts’ transfer performance.
Tag: ImageNet
Google & DeepMind Researchers Revamp ImageNet
Google Brain in Zürich and DeepMind London researchers believe one of the world’s most popular image databases may need a makeover.
NeurIPS 2020 Changes Review Process; Hinton & Google Brain Unsupervised Model Boosts ImageNet Accuracy 7%; DeepMind Releases New JAX Libraries
Synced Global AI Weekly February 23rd
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.
AAAI 2020 Best Papers; Turing Award Winners See a Turning Point for Deep Learning; MIT Reveals Voting App Vulnerabilities
Synced Global AI Weekly February 16th
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.
Natural Adversarial Examples Slash Image Classification Accuracy by 90%
Researchers from UC Berkeley and the Universities of Washington and Chicago have released a set of natural adversarial examples, which they call “ImageNet-A.”
Facebook Model Pretrained on Billions of Instagram Hashtags Achieves SOTA Results on Top-1 ImageNet
Facebook AI research team show how they trained a large convolutional network to predict hashtags on some 3.5 billion social media images. The research returned a state-of-the-art top-1 accuracy result of 85.4 percent on ImageNet.
New DeepMind Unsupervised Image Model Challenges AlexNet
A new paper from Google’s UK-based research company DeepMind addresses this with a model based on Contrastive Predictive Coding (CPC) that outperforms the fully-supervised AlexNet model in Top-1 and Top-5 accuracy on ImageNet.
Megvii Introduces Single-Path, One-Shot Method for NAS Design
Chinese AI unicorn Megvii Technology has proposed a new single-path, one-shot NAS design approach which makes various applications more convenient and achieves start-of-the-art performance on the large dataset ImageNet.
SenseTime Trains ImageNet/AlexNet In Record 1.5 minutes
Researchers from Beijing-based AI unicorn SenseTime and Nanyang Technological University have trained ImageNet/AlexNet in a record-breaking 1.5 minutes, a significant 2.6 times speedup over the previous record of 4 minutes.
FAIR Paper Questions Pre-Training’s Efficacy in CV
ImageNet Pre-training is common in a variety of CV (Computer Vision) tasks, as something of a consensus has emerged that pre-training can help a model learn transferrable information that can be useful for target tasks.
Global Companies Are Making AI Breakthroughs
Synced Global AI Weekly November 25th
Sony Breaks ResNet-50 Training Record on ImageNet
Researchers from Japanese electronics giant Sony have trained the ResNet-50 neural network model on ImageNet in a record-breaking 224 seconds — 43.4 percent better than the previous fastest time for the benchmark task.
OpenAI Founder: Short-Term AGI Is a Serious Possibility
Artificial general intelligence (AGI) is the long-range, human-intelligence-level target of contemporary AI researchers worldwide. It’s believed AGI has the potential to meet basic human needs globally, end poverty, cure diseases, extend life, and even mitigate climate change. In short, AGI is the tech that could not only save the world, but build a utopia.
Tencent ML Team Trains ImageNet In Record Four Minutes
Since 2010, the annual ImageNet Large-Scale Visual Recognition Challenge has been the most widely recognized benchmark for testing image recognition algorithms. Tencent Machine Learning picks up the challenge with its new paper Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes.
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
The ShuffleNet utilizes pointwise group convolution and channel shuffle to reduce computation cost while maintaining accuracy. It manages to obtain lower top-1 error than the MobileNet system on ImageNet classification, and achieves ~13x actual speedup over AlexNet while maintaining comparable accuracy.
CVPR2017 Honorable Mention Paper – Annotating Object Instances with a Polygon-RNN
This paper proposes not only a method as a useful tool but also a new concept for modeling complex annotation as a simple polygon.
Understanding the Mechanisms of Deep Transfer Learning for Medical Images
This paper systematically studies how a convolutional neural network, trained on ImageNet for image classification tasks, works on medical images – or more precisely on ultrasound images – for the “Kidney Detection” problem.
The Humans Behind Artificial Intelligence
AI companies require accurate data for specialized applications, and seemingly little things such as labelling and tagging demand accuracy. At present, only humans are up for the task.
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
This paper proposed a computationally efficient convolutional layer to upscale the final low-resolution feature map to a high-resolution output.