Tasks

Zero-Shot Image Classification

Zero shot image classification is the task of classifying previously unseen classes during training of a model.

Inputs
Classes

cat, dog, bird

Zero-Shot Image Classification Model
Output
Cat
0.664
Dog
0.329
Bird
0.008

Compatible libraries

Zero-Shot Image Classification demo
Models for Zero-Shot Image Classification
Browse Models (238)

Note Robust image classification model trained on publicly available image-caption data.

Note Robust image classification model trained on publicly available image-caption data trained on additional high pixel data for better performance.

Datasets for Zero-Shot Image Classification
Browse Datasets (158)

No example dataset is defined for this task.

Note Contribute by proposing a dataset for this task !

Spaces using Zero-Shot Image Classification

No example Space is defined for this task.

Note Contribute by proposing a Space for this task !

Metrics for Zero-Shot Image Classification
top-K accuracy
Computes the number of times the correct label appears in top K labels predicted