Local Convolutional Features with Unsupervised Training for Image Retrieval
Abstract
Patch-level descriptors underlie several important computer vision tasks, such as stereo-matching or content-based image retrieval. We introduce a deep convolutional architecture that yields patch-level descriptors, as an alternative to the popular SIFT descriptor for image retrieval. The proposed family of descriptors, called Patch-CKN, adapt the recently introduced Convolutional Kernel Network (CKN), an unsupervised framework to learn convolutional architectures. We present a comparison framework to benchmark current deep convolutional approaches along with Patch-CKN for both patch and image retrieval, including our novel ``RomePatches'' dataset. Patch-CKN descriptors yield competitive results compared to supervised CNNs alternatives on patch and image retrieval.
Fichier principal
deep_patches.pdf (3.14 Mo)
Télécharger le fichier
figure_deep_kernel_2layer.jpg (143.58 Ko)
Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)
Loading...