-
Caltech-UCSD Birds
Caltech-UCSD Birds (CUB 200-2007) and extended version CUB 200-2011 image collections tagged with keypoints, bounding boxes, coarse segmentation, and attribute labels. -
CUB dataset
The CUB dataset is a large collection of images of birds, each image is a 299x299 RGB image, and there are 11,778 training images and 5,994 testing images. -
Waterbirds
Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers... -
The Caltech-UCSD Birds-200-2011 Dataset
The CUB dataset is a collection of images of landbirds and waterbirds from the CUB dataset, combined with images from Places dataset as background.