106 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.
Large datasets often contain overly similar examples that consume training cycles without contributing to learning. A new paper identifies similar training examples, even if they’re not labeled.
Large datasets often contain overly similar examples that consume training cycles without contributing to learning. A new paper identifies similar training examples, even if they’re not labeled.
Neural networks can describe in words what’s happening in pictures and videos — but can they make sensible guesses about things that happened before or will happen afterward? Researchers probed this ability.
Neural networks can describe in words what’s happening in pictures and videos — but can they make sensible guesses about things that happened before or will happen afterward? Researchers probed this ability.
When a neural network learns image labels, it may confuse a background item for the labeled object. New research avoids such mistakes.
When a neural network learns image labels, it may confuse a background item for the labeled object. New research avoids such mistakes.
Convolutional neural networks separate proteins into functional families without considering their shapes.
Convolutional neural networks separate proteins into functional families without considering their shapes.
Images in the wild may not come with labels, but they often include metadata. A new training method takes advantage of this information to improve contrastive learning.
Images in the wild may not come with labels, but they often include metadata. A new training method takes advantage of this information to improve contrastive learning.
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.
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.
An object detector trained exclusively on urban images might mistake a moose for a pedestrian and express high confidence in its poor judgment. New work enables object detectors, and potentially other neural networks, to lower their confidence when they encounter unfamiliar inputs.
Stay updated with weekly AI News and Insights delivered to your inbox