ResNet

49 Posts

Animated chart shows how AI can avoid mistaking an image's subject for its context.
ResNet

Taming Spurious Correlations: New Technique Helps AI Avoid Classification Mistakes

When a neural network learns image labels, it may confuse a background item for the labeled object. New research avoids such mistakes.
2 min read
Animated flowcharts show how the ProtCNN AI model classifies proteins.
ResNet

Protein Families Deciphered: Machine Learning Categorizes Proteins Based on Their Functions

Convolutional neural networks separate proteins into functional families without considering their shapes.
2 min read
Flowcharts show how a new contrastive learning approach uses metadata to improve AI image classifiers.
ResNet

Learning From Metadata: Descriptive Text Improves Performance for AI Image Classification Systems

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.
2 min read
Tradeoffs for Higher Accuracy
ResNet

Tradeoffs for Higher Accuracy

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.
2 min read
Right-Sizing Confidence
ResNet

Right-Sizing Confidence

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
2 min read
Less Data for Vision Transformers
ResNet

Less Data for Vision Transformers

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.
2 min read
Graph
ResNet

The Limits of Pretraining

The higher the accuracy of a pretrained model, the better its performance after fine-tuning, right? Not necessarily.What’s new: Samira Abnar and colleagues at Google Research conducted
2 min read
Transformer Architecture
ResNet

Transformers See in 3D

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
3 min read
Animation showing how MERLOT is able to match contextualized captions with their corresponding video frames
ResNet

Richer Video Representations: Pretraining Method Improves AI's Ability to Understand Video

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.
2 min read
Animation showing Hierarchical Outlier Detection (HOD)
ResNet

Oddball Recognition: New Method Identifies Outliers in AI Training Data

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.
2 min read
Animated charts showing how AI can learn from simple tasks to harder versions of the same task
ResNet

More Thinking Solves Harder Problems: AI Can Learn From Simple Tasks to Solve Hard Problems

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.
2 min read
Information about a new unsupervised pretraining method called VICReg
ResNet

More Reliable Pretraining: Pretraining Method Helps AI Learn Useful Representations

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.
2 min read
Different x-rays and CT scans displayed
ResNet

AI Sees Race in X-Rays

Researchers from Emory University, MIT, Purdue University, and other institutions found that deep learning systems trained to interpret x-rays and CT scans also were able to identify their subjects as Asian, Black, or White.
2 min read
Image recognition examples
ResNet

Smaller Models, Bigger Biases

Compression methods like parameter pruning and quantization can shrink neural networks for use in devices like smartphones with little impact on accuracy — but they also exacerbate a network’s bias.
2 min read
Series of images showing how single trained network generates 3D reconstructions of multiple scenes
ResNet

One Network, Many Scenes

To reconstruct the 3D world behind a set of 2D images, machine learning systems usually require a dedicated neural network for each scene. New research enables a single trained network to generate 3D reconstructions of multiple scenes.
2 min read

Subscribe to The Batch

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