Trevor Darrell
(10 articles)
Active Learning
A strategy in ML where the model selectively queries the most informative data points from an unlabeled dataset to maximize its learning efficiency.
Generality: 775
Model Compression
Techniques designed to reduce the size of a machine learning model without significantly sacrificing its accuracy.
Generality: 715
Landmarks
Key points in an image used as reference for computer vision and AI systems to understand and manipulate visual data.
Generality: 500
Image-to-Text Model
AI systems that convert visual information from images into descriptive textual representations, enabling machines to understand and communicate the content of images.
Generality: 755
FCN
Fully Convolutional Networks
Fully Convolutional Networks
Neural network architecture designed specifically for image segmentation tasks, where the goal is to classify each pixel of an image into a category.
Generality: 760
FSL
Few-Shot Learning
Few-Shot Learning
ML approach that enables models to learn and make accurate predictions from a very small dataset.
Generality: 575
Out of Distribution
Data that differs significantly from the training data used to train a machine learning model, leading to unreliable or inaccurate predictions.
Generality: 675
TTT
Test-Time Training
Test-Time Training
ML approach where the model adapts itself during the inference phase using auxiliary tasks and additional training data available at test time to improve performance.
Generality: 325
ITM
Image-Text Matching
Image-Text Matching
AI technique that involves automatically identifying correspondences between textual descriptions and visual elements within images.
Generality: 480
VLM
Visual Language Model
Visual Language Model
AI models designed to interpret and generate content by integrating visual and textual information, enabling them to perform tasks like image captioning, visual question answering, and more.
Generality: 621