Skip to Main content Skip to Navigation
Conference papers

Local Convolutional Features with Unsupervised Training for Image Retrieval

Mattis Paulin 1 Matthijs Douze 1 Zaid Harchaoui 1 Julien Mairal 1 Florent Perronnin 2 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology, LJK - Laboratoire Jean Kuntzmann, Inria Grenoble - Rhône-Alpes
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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [42 references]  Display  Hide  Download
Contributor : Thoth Team <>
Submitted on : Thursday, October 1, 2015 - 4:27:12 PM
Last modification on : Tuesday, December 8, 2020 - 10:35:48 AM
Long-term archiving on: : Saturday, January 2, 2016 - 11:20:59 AM


Files produced by the author(s)




Mattis Paulin, Matthijs Douze, Zaid Harchaoui, Julien Mairal, Florent Perronnin, et al.. Local Convolutional Features with Unsupervised Training for Image Retrieval. ICCV - IEEE International Conference on Computer Vision, Dec 2015, Santiago, Chile. pp.91-99, ⟨10.1109/ICCV.2015.19⟩. ⟨hal-01207966⟩



Record views


Files downloads