Convolutional Patch Representations for Image Retrieval: an Unsupervised Approach - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles International Journal of Computer Vision Year : 2017

Convolutional Patch Representations for Image Retrieval: an Unsupervised Approach


Convolutional neural networks (CNNs) have recently received a lot of attention due to their ability to model local stationary structures in natural images in a multi-scale fashion, when learning all model parameters with supervision. While excellent performance was achieved for image classification when large amounts of labeled visual data are available, their success for un-supervised tasks such as image retrieval has been moderate so far. Our paper focuses on this latter setting and explores several methods for learning patch descriptors without supervision with application to matching and instance-level retrieval. To that effect, we propose a new family of convolutional descriptors for patch representation , based on the recently introduced convolutional kernel networks. We show that our descriptor, named Patch-CKN, performs better than SIFT as well as other convolutional networks learned by artificially introducing supervision and is significantly faster to train. To demonstrate its effectiveness, we perform an extensive evaluation on standard benchmarks for patch and image retrieval where we obtain state-of-the-art results. We also introduce a new dataset called RomePatches, which allows to simultaneously study descriptor performance for patch and image retrieval.
Fichier principal
Vignette du fichier
deep_patches_ijcv.pdf (3.4 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01277109 , version 1 (22-02-2016)
hal-01277109 , version 2 (01-03-2016)



Mattis Paulin, Julien Mairal, Matthijs Douze, Zaid Harchaoui, Florent Perronnin, et al.. Convolutional Patch Representations for Image Retrieval: an Unsupervised Approach. International Journal of Computer Vision, 2017, 121 (1), pp.149-168. ⟨10.1007/s11263-016-0924-3⟩. ⟨hal-01277109v2⟩
1040 View
1281 Download



Gmail Facebook X LinkedIn More