17th May - 30th May 2019
Etymo Newsletter provides the latest development in machine learning research,
including the most popular datasets and the most trending papers in the past two weeks.
If you like this newsletter, you can subscribe to our fortnightly newsletters here.
Fortnight Summary
Popular datasets include MNIST, CIFAR-10, ImageNet, CelebA, and KITTI. Our trending phrases are Security Event, Dropout Samples, and Social Learning. Three trending papers are related to a review of object detection in the past 20 years, a new and efficient scaling method for CNN, and a few-shot system of neural talking head models. We also present you a collection of recent summaries about advancement in machine learning.Popular Datasets
Here are most mentioned datasets over the last two weeks.
| Name | Type | Number of Papers |
|---|---|---|
| MNIST | Handwritten Digits | 142 |
| CIFAR-10 | Tiny Image Dataset in 10 Classes | 82 |
| ImageNet | Image Dataset | 64 |
| CelebA | Large-scale CelebFaces Attributes (CelebA) Dataset | 22 |
| KITTI | Autonomous Driving | 21 |
Trending Phrases
In this section, we present a list of phrases that appeared significantly more in this newsletter than the previous newsletters.
- Security Event:
- Tiresias: Predicting Security Events Through Deep Learning
- Multi-Sample Dropout for Accelerated Training and Better Generalization
- Non-Bayesian Social Learning with Imperfect Private Signal Structure
Dropout Samples:
Social Learning:
Etymo Trending
Presented below is a list of the most trending papers added in the last two weeks.
-
Object Detection in 20 Years: A Survey:
An extensive review of over 400 papers about object detection in the light of its technical evolution, spanning over a quarter-century's time (from the 1990s to 2019). Topics covered by this paper include the milestone detectors in history, detection datasets, metrics, fundamental building blocks of the detection system, speed up techniques, the recent state of the art detection methods, and important detection applications. -
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks:
A new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient. The authors demonstrate the effectiveness of this method on scaling up MobileNets and ResNet. Source code of EfficientNet is also available. -
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models:
A realistic personalized talking head system that can learn from a few image views of a person, potentially even a single image. The system performs lengthy meta-learning on a large dataset of videos, and is able to frame few- and one-shot learning of neural talking head models of previously unseen people as adversarial training problems with high capacity generators and discriminators. It is able to initialize the parameters of both the generator and the discriminator in a person-specific way, so that training can be based on just a few images and done quickly, despite the need to tune tens of millions of parameters.
Papers on Machine Learning Application
- Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition: A Problem-Oriented Perspective
- Machine Learning for Fluid Mechanics
- A high-bias, low-variance introduction to Machine Learning for physicists
- Leveraging Machine Learning and Big Data for Smart Buildings: A Comprehensive Survey
- Decision Tree Classification with Differential Privacy: A Survey
- Visual Analytics of Anomalous User Behaviors: A Survey