14 datasets found

The Taskonomy dataset contains 16 types of annotation, including object classification, scene classification, depth estimation, surface normals, curvature estimation, edge...

We use the MIT Indoor-67 dataset for scene classification.

UC-Merced dataset for scene classification.

The AID dataset is a benchmark for scene classification in remote sensing. It contains aerial images with 30 scene types.

The SUNRGB-D dataset features 5,285 training and 5,050 test samples from multiple RGB-D cameras. The dataset provides annotations for the first 37 NYUv2 semantic classes and for...

Remote sensing image scene classification dataset

UC Merced Land Use Dataset (Yang & Newsam, 2010) contains remote sensing satellite images of 21 classes, with 100 images in each class.

The SUN attribute dataset is a collection of images of scenes.

Multi-task learning (MTL) research is broadly divided into two categories: one is to learn the correlation between tasks through model structures, and the other is to balance...

MIT Places2 is a scene-centric dataset with more than 10 million images consisting of over 400 unique scene classes.

The Optimal-31 dataset [82] was created in 2017 by Northwestern Polytechnical University, China.

NWPU-RESISC45 dataset was collected from more than 100 countries and regions in the world, consists of 31,500 remote sensing images.

Remote sensing scene classification has been extensively studied for its critical roles in geological survey, oil exploration, traffic management, earthquake prediction,...

The AID dataset is a benchmark dataset for performance evaluation of aerial scene classification.