Pre-extracted GoogLeNet features for the vision benchmark datasets
used in the experiments of our paper.
Files
cifar_googlenet.mat— CIFAR-10 featuresmnist_googlenet.mat— MNIST featuresf_mnist_googlenet.mat— Fashion-MNIST features
Notes
Features were extracted using a pre-trained GoogLeNet network.
For the real-world partial label datasets (MIRFlickr, MSRCv2),
download directly from https://palm.seu.edu.cn/zhangml/Resources.htm
and place in the data/ folder.