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. 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.
@article{
title = {Local convolutional features with unsupervised training for image retrieval},
type = {article},
year = {2015},
pages = {91-99},
volume = {2015 Inter},
id = {d7f0af5e-28b9-3cb9-9508-63836ad2cf16},
created = {2022-09-19T09:01:24.792Z},
file_attached = {true},
profile_id = {276016a7-2c9d-3507-8888-093db7c54774},
group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
last_modified = {2022-09-19T09:02:57.931Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100},
private_publication = {false},
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 CNN alternatives on patch and image retrieval.},
bibtype = {article},
author = {Paulin, Mattis and Douze, Matthijs and Harchaoui, Zaid and Mairal, Julien and Perronin, Florent and Schmid, Cordelia},
doi = {10.1109/ICCV.2015.19},
journal = {Proceedings of the IEEE International Conference on Computer Vision}
}
Downloads: 0
{"_id":"SXQERJAFM96MbWyak","bibbaseid":"paulin-douze-harchaoui-mairal-perronin-schmid-localconvolutionalfeatureswithunsupervisedtrainingforimageretrieval-2015","author_short":["Paulin, M.","Douze, M.","Harchaoui, Z.","Mairal, J.","Perronin, F.","Schmid, C."],"bibdata":{"title":"Local convolutional features with unsupervised training for image retrieval","type":"article","year":"2015","pages":"91-99","volume":"2015 Inter","id":"d7f0af5e-28b9-3cb9-9508-63836ad2cf16","created":"2022-09-19T09:01:24.792Z","file_attached":"true","profile_id":"276016a7-2c9d-3507-8888-093db7c54774","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2022-09-19T09:02:57.931Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"folder_uuids":"02fb5526-03ff-44ad-8d5c-42bd496c3100","private_publication":false,"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 CNN alternatives on patch and image retrieval.","bibtype":"article","author":"Paulin, Mattis and Douze, Matthijs and Harchaoui, Zaid and Mairal, Julien and Perronin, Florent and Schmid, Cordelia","doi":"10.1109/ICCV.2015.19","journal":"Proceedings of the IEEE International Conference on Computer Vision","bibtex":"@article{\n title = {Local convolutional features with unsupervised training for image retrieval},\n type = {article},\n year = {2015},\n pages = {91-99},\n volume = {2015 Inter},\n id = {d7f0af5e-28b9-3cb9-9508-63836ad2cf16},\n created = {2022-09-19T09:01:24.792Z},\n file_attached = {true},\n profile_id = {276016a7-2c9d-3507-8888-093db7c54774},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2022-09-19T09:02:57.931Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100},\n private_publication = {false},\n 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 CNN alternatives on patch and image retrieval.},\n bibtype = {article},\n author = {Paulin, Mattis and Douze, Matthijs and Harchaoui, Zaid and Mairal, Julien and Perronin, Florent and Schmid, Cordelia},\n doi = {10.1109/ICCV.2015.19},\n journal = {Proceedings of the IEEE International Conference on Computer Vision}\n}","author_short":["Paulin, M.","Douze, M.","Harchaoui, Z.","Mairal, J.","Perronin, F.","Schmid, C."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/1b966d21-1f58-9a5b-5f1a-3cd5a3685bd6/paulin2015.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"paulin-douze-harchaoui-mairal-perronin-schmid-localconvolutionalfeatureswithunsupervisedtrainingforimageretrieval-2015","role":"author","metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["aXmRAq63YsH7a3ufx","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["local","convolutional","features","unsupervised","training","image","retrieval","paulin","douze","harchaoui","mairal","perronin","schmid"],"title":"Local convolutional features with unsupervised training for image retrieval","year":2015}