TY - GEN

T1 - Fine-grained categorization and dataset bootstrapping using deep metric learning with humans in the loop

AU - Cui, Yin

AU - Zhou, Feng

AU - Lin, Yuanqing

AU - Belongie, Serge

N1 - Publisher Copyright: © 2016 IEEE.

PY - 2016/12/9

Y1 - 2016/12/9

N2 - Existing fine-grained visual categorization methods often suffer from three challenges: lack of training data, large number of fine-grained categories, and high intraclass vs. low inter-class variance. In this work we propose a generic iterative framework for fine-grained categorization and dataset bootstrapping that handles these three challenges. Using deep metric learning with humans in the loop, we learn a low dimensional feature embedding with anchor points on manifolds for each category. These anchor points capture intra-class variances and remain discriminative between classes. In each round, images with high confidence scores from our model are sent to humans for labeling. By comparing with exemplar images, labelers mark each candidate image as either a 'true positive' or a 'false positive.' True positives are added into our current dataset and false positives are regarded as 'hard negatives' for our metric learning model. Then the model is retrained with an expanded dataset and hard negatives for the next round. To demonstrate the effectiveness of the proposed framework, we bootstrap a fine-grained flower dataset with 620 categories from Instagram images. The proposed deep metric learning scheme is evaluated on both our dataset and the CUB-200-2001 Birds dataset. Experimental evaluations show significant performance gain using dataset bootstrapping and demonstrate state-of-the-art results achieved by the proposed deep metric learning methods.

AB - Existing fine-grained visual categorization methods often suffer from three challenges: lack of training data, large number of fine-grained categories, and high intraclass vs. low inter-class variance. In this work we propose a generic iterative framework for fine-grained categorization and dataset bootstrapping that handles these three challenges. Using deep metric learning with humans in the loop, we learn a low dimensional feature embedding with anchor points on manifolds for each category. These anchor points capture intra-class variances and remain discriminative between classes. In each round, images with high confidence scores from our model are sent to humans for labeling. By comparing with exemplar images, labelers mark each candidate image as either a 'true positive' or a 'false positive.' True positives are added into our current dataset and false positives are regarded as 'hard negatives' for our metric learning model. Then the model is retrained with an expanded dataset and hard negatives for the next round. To demonstrate the effectiveness of the proposed framework, we bootstrap a fine-grained flower dataset with 620 categories from Instagram images. The proposed deep metric learning scheme is evaluated on both our dataset and the CUB-200-2001 Birds dataset. Experimental evaluations show significant performance gain using dataset bootstrapping and demonstrate state-of-the-art results achieved by the proposed deep metric learning methods.

UR - http://www.scopus.com/inward/record.url?scp=84986332657&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2016.130

DO - 10.1109/CVPR.2016.130

M3 - Conference article

AN - SCOPUS:84986332657

SP - 1153

EP - 1162

JO - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings

JF - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings

SN - 1063-6919

T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

Y2 - 26 June 2016 through 1 July 2016

ER -