Augmentation

13 Posts

Two randomly cropped pictures
Augmentation

Tradeoffs for Higher Accuracy: Data Augmentation Plus Weight Decay can Boost Some AI Models

Vision models can be improved by training them on several altered versions of the same image and also by encouraging their weights to be close to zero. Recent research showed that both can have adverse effects that may be difficult to detect.
Diagram with automated decision systems
Augmentation

Roadblocks to Regulation: Why laws to regulate AI usually fail.

Most U.S. state agencies use AI without limits or oversight. An investigative report probed reasons why efforts to rein them in have made little headway. Since 2018, nearly every proposed bill aimed at studying or controlling how state agencies use automated decision systems.
Contrast between real and real and synthetic datasets
Augmentation

Battling Bias in Synthetic Data

Synthetic datasets can inherit flaws in the real-world data they’re based on. Startups are working on solutions. Generating synthetic datasets for training machine learning systems is a booming business.
Examples of AI generated images
Augmentation

GANs for Smaller Data

Trained on a small dataset, generative adversarial networks (GANs) tend to generate either replicas of the training data or noisy output. A new method spurs them to produce satisfying variations.
Examples of CT scans with different contrasts
Augmentation

More Data for Medical AI

Convolutional neural networks are good at recognizing disease symptoms in medical scans of patients who were injected with iodine-based dye, that makes their organs more visible. But some patients can’t take the dye. Now synthetic scans from a GAN are helping CNNs learn to analyze undyed images.
Data and graphs related to a method that synthesizes extracted features of underrepresented classes
Augmentation

Augmentation for Features

In any training dataset, some classes may have relatively few examples. A new technique can improve a trained model’s performance on such underrepresented classes. Researchers introduced a method that synthesizes extracted features of underrepresented classes.
Data and information related to shortcut learning
Augmentation

When Models Take Shortcuts

Neuroscientists once thought they could train rats to navigate mazes by color. Rats don’t perceive colors at all. Instead, they rely on the distinct odors of different colors of paint. New work finds that neural networks are prone to this sort of misalignment between training goals and learning.
Self-driving car from the inside
Augmentation

Cars Idled, AV Makers Keep Rolling

The pandemic has forced self-driving car companies off the road. Now they’re moving forward by refining their mountains of training data. Self-driving cars typically collect real-world training data with two human operators onboard, but Covid-19 makes that unsafe at any speed.
Information and examples of CheXbert, a network that labels chest X-rays
Augmentation

Human-Level X-Ray Diagnosis

Like nurses who can’t decipher a doctor’s handwriting, machine learning models can’t decipher medical scans — without labels. Conveniently, natural language models can read medical records to extract labels for X-ray images.
Examples of recognition of real and fake images
Augmentation

Fake Detector

AI’s ability to produce synthetic pictures that fool humans into believing they’re real has spurred a race to build neural networks that can tell the difference. Recent research achieved encouraging results.
Scans representing pedestrians and other objects
Augmentation

Data Augmentation in 3D

An unconventional approach to modifying data is cutting the amount of work required to train self-driving cars. Waymo unveiled a machine learning pipeline that varies lidar scans representing pedestrians and other objects.
Good and bad examples of labeling images with pictures of birds
Augmentation

Selling Shovels to Data Miners

When the world is panning for machine learning gold, it pays to help them dig through the data. Machine learning entrepreneurs can make their mark (and their fortune) building services that help other companies develop, deploy, and monitor AI, venture capitalist Rob Toews argues in Forbes.
FixMatch example
Augmentation

Less Labels, More Learning

In small data settings where labels are scarce, semi-supervised learning can train models by using a small number of labeled examples and a larger set of unlabeled examples. A new method outperforms earlier techniques.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox