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