Caltech-101

홈페이지 · 논문 709편

The Caltech101 dataset contains images from 101 object categories (e.g., “helicopter”, “elephant” and “chair” etc.) and a background category that contains the images not from the 101 object categories. For each object category, there are about 40 to 800 images, while most classes have about 50 images. The resolution of the image is roughly about 300×200 pixels. Source: Simple and Efficient Learning using Privileged Information

Images

벤치마크

Fine-Grained Image Classification on Caltech-101 결과 36개

Prompt Engineering on Caltech-101 결과 14개

Semantic correspondence on Caltech-101 결과 4개

Density Estimation on Caltech-101 결과 3개

Semi-Supervised Image Classification on Caltech-101 결과 2개

Semi-Supervised Image Classification on Caltech-101, 202 Labels 결과 2개

Unsupervised Anomaly Detection on Caltech-101 결과 2개

Zero-Shot Learning on Caltech-101 결과 2개

Image Clustering on Caltech-101 결과 1개

Transductive Zero-Shot Classification on Caltech-101 결과 1개