ResNet

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.

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.

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.

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.

Vision Transformer (ViT) outperformed convolutional neural networks in image classification, but it required more training data. New work enabled ViT and its variants to outperform other architectures with less training data.

The higher the accuracy of a pretrained model, the better its performance after fine-tuning, right? Not necessarily. Researchers conducted a meta-analysis of image-recognition experiments and performed some of their own.

Visual robots typically perceive the three-dimensional world through sequences of two-dimensional images, but they don’t always know what they’re looking at. For instance, Tesla’s self-driving system has been known to mistake a full moon for a traffic light.

To understand a movie scene, viewers often must remember or infer previous events and extrapolate potential consequences. New work improved a model’s ability to do the same.

Models trained using supervised learning struggle to classify inputs that differ substantially from most of their training data. A new method helps them recognize such outliers.

In machine learning, an easy task and a more difficult version of the same task — say, a maze that covers a smaller or larger area — often are learned separately.

Pretraining methods generate basic representations for later fine-tuning, but they’re prone to certain issues that can throw them off-kilter. New work proposes a solution.