@article{
 title = {FaceNet: A Unified Embedding for Face Recognition and Clustering http://arxiv.org/abs/1503.03832 (Google Research) #ml #dlearn pic.twitter.com/fFotqHa1HC},
 type = {article},
 year = {2015},
 pages = {815-823},
 websites = {https://arxiv.org/abs/1503.03832},
 id = {3464aa16-3ba5-3d65-93ff-4e2bced593f7},
 created = {2022-09-19T10:49:12.316Z},
 file_attached = {true},
 profile_id = {276016a7-2c9d-3507-8888-093db7c54774},
 group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
 last_modified = {2022-09-19T10:50:22.430Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100},
 private_publication = {false},
 abstract = {Despite significant recent advances in the field of face recognition [10, 14, 15, 17], implementing face verification and recognition efficiently at scale presents serious chal- lenges to current approaches. In this paper we present a system, called FaceNet, that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure of face similarity. Once this space has been produced, tasks such as face recogni- tion, verification and clustering can be easily implemented using standard techniques with FaceNet embeddings as fea- ture vectors. Our method uses a deep convolutional network trained to directly optimize the embedding itself, rather than an in- termediate bottleneck layer as in previous deep learning approaches. To train, we use triplets of roughly aligned matching / non-matching face patches generated using a novel online triplet mining method. The benefit of our approach is much greater representational efficiency: we achieve state-of-the-art face recognition performance using only 128-bytes per face. On the widely used Labeled Faces in the Wild (LFW) dataset, our system achieves a new record accuracy of 99.63%. On YouTube Faces DB it achieves 95.12%. Our system cuts the error rate in comparison to the best pub- lished result [15] by 30% on both datasets.},
 bibtype = {article},
 author = {Champandard, Alex J.},
 journal = {Proceedings of the IEEE conference on computer vision and pattern recognition}
}

{"_id":"2iCPXr54xoaq4vkdd","bibbaseid":"champandard-facenetaunifiedembeddingforfacerecognitionandclusteringhttparxivorgabs150303832googleresearchmldlearnpictwittercomffotqha1hc-2015","author_short":["Champandard, A., J."],"bibdata":{"title":"FaceNet: A Unified Embedding for Face Recognition and Clustering http://arxiv.org/abs/1503.03832 (Google Research) #ml #dlearn pic.twitter.com/fFotqHa1HC","type":"article","year":"2015","pages":"815-823","websites":"https://arxiv.org/abs/1503.03832","id":"3464aa16-3ba5-3d65-93ff-4e2bced593f7","created":"2022-09-19T10:49:12.316Z","file_attached":"true","profile_id":"276016a7-2c9d-3507-8888-093db7c54774","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2022-09-19T10:50:22.430Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"folder_uuids":"02fb5526-03ff-44ad-8d5c-42bd496c3100","private_publication":false,"abstract":"Despite significant recent advances in the field of face recognition [10, 14, 15, 17], implementing face verification and recognition efficiently at scale presents serious chal- lenges to current approaches. In this paper we present a system, called FaceNet, that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure of face similarity. Once this space has been produced, tasks such as face recogni- tion, verification and clustering can be easily implemented using standard techniques with FaceNet embeddings as fea- ture vectors. Our method uses a deep convolutional network trained to directly optimize the embedding itself, rather than an in- termediate bottleneck layer as in previous deep learning approaches. To train, we use triplets of roughly aligned matching / non-matching face patches generated using a novel online triplet mining method. The benefit of our approach is much greater representational efficiency: we achieve state-of-the-art face recognition performance using only 128-bytes per face. On the widely used Labeled Faces in the Wild (LFW) dataset, our system achieves a new record accuracy of 99.63%. On YouTube Faces DB it achieves 95.12%. Our system cuts the error rate in comparison to the best pub- lished result [15] by 30% on both datasets.","bibtype":"article","author":"Champandard, Alex J.","journal":"Proceedings of the IEEE conference on computer vision and pattern recognition","bibtex":"@article{\n title = {FaceNet: A Unified Embedding for Face Recognition and Clustering http://arxiv.org/abs/1503.03832 (Google Research) #ml #dlearn pic.twitter.com/fFotqHa1HC},\n type = {article},\n year = {2015},\n pages = {815-823},\n websites = {https://arxiv.org/abs/1503.03832},\n id = {3464aa16-3ba5-3d65-93ff-4e2bced593f7},\n created = {2022-09-19T10:49:12.316Z},\n file_attached = {true},\n profile_id = {276016a7-2c9d-3507-8888-093db7c54774},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2022-09-19T10:50:22.430Z},\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 = {Despite significant recent advances in the field of face recognition [10, 14, 15, 17], implementing face verification and recognition efficiently at scale presents serious chal- lenges to current approaches. In this paper we present a system, called FaceNet, that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure of face similarity. Once this space has been produced, tasks such as face recogni- tion, verification and clustering can be easily implemented using standard techniques with FaceNet embeddings as fea- ture vectors. Our method uses a deep convolutional network trained to directly optimize the embedding itself, rather than an in- termediate bottleneck layer as in previous deep learning approaches. To train, we use triplets of roughly aligned matching / non-matching face patches generated using a novel online triplet mining method. The benefit of our approach is much greater representational efficiency: we achieve state-of-the-art face recognition performance using only 128-bytes per face. On the widely used Labeled Faces in the Wild (LFW) dataset, our system achieves a new record accuracy of 99.63%. On YouTube Faces DB it achieves 95.12%. Our system cuts the error rate in comparison to the best pub- lished result [15] by 30% on both datasets.},\n bibtype = {article},\n author = {Champandard, Alex J.},\n journal = {Proceedings of the IEEE conference on computer vision and pattern recognition}\n}","author_short":["Champandard, A., J."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/15157aaf-48d1-4ba5-13b8-bac6f42e1f36/schroff2015.pdf.pdf","Website":"https://arxiv.org/abs/1503.03832"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"champandard-facenetaunifiedembeddingforfacerecognitionandclusteringhttparxivorgabs150303832googleresearchmldlearnpictwittercomffotqha1hc-2015","role":"author","metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["facenet","unified","embedding","face","recognition","clustering","http","arxiv","org","abs","1503","03832","google","research","dlearn","pic","twitter","com","ffotqha1hc","champandard"],"title":"FaceNet: A Unified Embedding for Face Recognition and Clustering http://arxiv.org/abs/1503.03832 (Google Research) #ml #dlearn pic.twitter.com/fFotqHa1HC","year":2015}