Find a model

8 models· Computer Vision

—

by Meta AI · 0 reviews

Foundation model for promptable visual segmentation in images and videos, enabling real-time object tracking and zero-shot generalization to unseen content.

Accuracy—

Speed—

Cost—

—

EfficientNet

by Google Research · 0 reviews

Family of convolutional neural networks that use compound scaling to uniformly scale depth, width, and resolution for efficient image classification.

Accuracy—

Speed—

Cost—

Ease of use—

Reliability—

Compare

—

MobileNet

by Google Research · 0 reviews

Lightweight family of convolutional neural networks designed for efficient inference on mobile and embedded devices with minimal computational overhead.

Accuracy—

Speed—

Cost—

Ease of use—

Reliability—

Compare

—

Inception v3

by Google Research · 0 reviews

Deep convolutional neural network trained on ImageNet for classifying images into object categories with high accuracy.

Accuracy—

Speed—

Cost—

Ease of use—

Reliability—

Compare

—

ResNet

by Microsoft Research · 0 reviews

Deep residual learning network architecture that enables training of very deep neural networks through skip connections for image classification tasks.

Accuracy—

Speed—

Cost—

Ease of use—

Reliability—

Compare

—

Vision Transformer (ViT)

by Google Research · 0 reviews

Applies transformers directly to image patches for classification; inspired many CV variants.

Accuracy—

Speed—