—
SAM 2
by Meta AI
Foundation model for promptable visual segmentation in images and videos, enabling real-time object tracking and zero-shot generalization to unseen content.
Computer Vision
Enables machines to interpret and understand visual information such as images and video.
by Meta AI
Foundation model for promptable visual segmentation in images and videos, enabling real-time object tracking and zero-shot generalization to unseen content.
by Google Research
Family of convolutional neural networks that use compound scaling to uniformly scale depth, width, and resolution for efficient image classification.
by Google Research
Lightweight family of convolutional neural networks designed for efficient inference on mobile and embedded devices with minimal computational overhead.
by Google Research
Deep convolutional neural network trained on ImageNet for classifying images into object categories with high accuracy.
by Microsoft Research
Deep residual learning network architecture that enables training of very deep neural networks through skip connections for image classification tasks.
by Google Research
Applies transformers directly to image patches for classification; inspired many CV variants.
by Ultralytics
The latest YOLO family model for real-time object detection, classification, and segmentation.
by Meta AI
A promptable zero-shot image segmentation model trained on 1.1B masks over 11M images.