Local convolutional features with unsupervised training for image retrieval. Paulin, M., Douze, M., Harchaoui, Z., Mairal, J., Perronin, F., & Schmid, C. Proceedings of the IEEE International Conference on Computer Vision, 2015 Inter:91-99, 2015.
Local convolutional features with unsupervised training for image retrieval [pdf]Paper  doi  abstract   bibtex   
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 CNN alternatives on patch and image retrieval.

Downloads: 0