DeLF-pytorch
DeLF-pytorch copied to clipboard
what is the difference between the finetune dataset and the keypoint dataset?
finetune and pca trained with clean datasets, and keypoint dataset trained with full datasets
Could you please tell me where I can get the clean datasets and full datasets?
i want know it too
in the paper "In the dataset, there are the “full” version, referred to as LF (after removal of overlapping classes with Oxf5k/Par6k, by [11]), containing 140,372 images from 586 landmarks, and the “clean” version (LC) obtained by a SIFT-based matching procedure [11], with 35,382 images of 586 landmarks. We use LF to train our attention model, and LC is employed to fine-tune the network for image retrieval."