TY - GEN
T1 - Repmet
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
AU - Karlinsky, Leonid
AU - Shtok, Joseph
AU - Harary, Sivan
AU - Schwartz, Eli
AU - Aides, Amit
AU - Feris, Rogerio
AU - Giryes, Raja
AU - Bronstein, Alex M.
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples. In this work, we propose a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process. Our approach outperforms state-of-the-art methods for DML-based object classification on a variety of standard fine-grained datasets. Furthermore, we demonstrate the effectiveness of our approach on the problem of few-shot object detection, by incorporating the proposed DML architecture as a classification head into a standard object detection model. We achieve the best results on the ImageNet-LOC dataset compared to strong baselines, when only a few training examples are available. We also offer the community a new episodic benchmark based on the ImageNet dataset for the few-shot object detection task.
AB - Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples. In this work, we propose a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process. Our approach outperforms state-of-the-art methods for DML-based object classification on a variety of standard fine-grained datasets. Furthermore, we demonstrate the effectiveness of our approach on the problem of few-shot object detection, by incorporating the proposed DML architecture as a classification head into a standard object detection model. We achieve the best results on the ImageNet-LOC dataset compared to strong baselines, when only a few training examples are available. We also offer the community a new episodic benchmark based on the ImageNet dataset for the few-shot object detection task.
KW - Categorization
KW - Deep Learning
KW - Recognition: Detection
KW - Representation Learning
KW - Retrieval
UR - http://www.scopus.com/inward/record.url?scp=85077815819&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2019.00534
DO - 10.1109/CVPR.2019.00534
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85077815819
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 5192
EP - 5201
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PB - IEEE Computer Society
Y2 - 16 June 2019 through 20 June 2019
ER -