ImageNet

Vision transformers have bested convolutional neural networks (CNNs) in a number of key vision tasks. Have CNNs hit their limit? New research suggests otherwise.

Vision transformers typically process images in patches of fixed size. Smaller patches yield higher accuracy but require more computation. A new training method lets AI engineers adjust the tradeoff.

A tweak to diffusion models, which are responsible for most of the recent excitement about AI-generated images, enables them to produce more realistic output.

Stable Diffusion may amplify biases in its training data in ways that promote deeply ingrained social stereotypes.

Vision Transformers (ViTs) are overtaking convolutional neural networks (CNN) in many vision tasks, but procedures for training them are still tailored for CNNs. New research investigated how various training ingredients affect ViT performance.

From language to vision models, deep neural networks are marked by improved performance, higher efficiency, and better generalizations. Yet, these systems are also marked by perpetuation of bias and injustice.

The transformer architecture is notoriously inefficient when processing long sequences — a problem in processing images, which are essentially long sequences of pixels. One way around this is to break up input images and process the pieces

Key machine learning datasets are riddled with mistakes. Several benchmark datasets are shot through with incorrect labels. On average, 3.4 percent of examples in 10 commonly used datasets are mislabeled and the detrimental impact of such errors rises with model size.

ImageNet now comes with privacy protection.What’s new: The team that manages the machine learning community’s go-to image dataset blurred all the human faces pictured in it and tested how models trained on the modified images on a variety of image recognition tasks.

It’s well established that pretraining a model on a large dataset improves performance on fine-tuned tasks. In sufficient quantity and paired with a big model, even data scraped from the internet at random can contribute to the performance boost.

It’s commonly assumed that models pretrained to achieve high performance on ImageNet will perform better on other visual tasks after fine-tuning. But is it always true? A new study reached surprising conclusions.

The same models trained on the same data may show the same performance in the lab, and yet respond very differently to data they haven’t seen before. New work finds this inconsistency to be pervasive.

With access to a trained model, an attacker can use a reconstruction attack to approximate its training data. A method called InstaHide recently won acclaim for promising to make such examples unrecognizable to human eyes while retaining their utility for training.

Some of deep learning’s bedrock datasets came under scrutiny as researchers combed them for built-in biases. Researchers found that popular datasets impart biases against socially marginalized groups to trained models due to the ways the datasets were compiled, labeled, and used.

Social biases are well documented in decisions made by supervised models trained on ImageNet’s labels. But they also crept into the output of unsupervised models pretrained on the same dataset.