Margin-based Sampling in Deep Metric Learning
Authors: 
Shangwei Zhou, Qingsong Yu, Jun SunAuthors Info & Claims
Pages 277 - 280
Abstract
Deep metric learning is routinely trained with a pair or a triplet of data samples, either of which converges slowly. It is usually to adopt hard negative mining for a fast convergence. Many existing methods train with the hardest examples, which are selected by ranking or scoring the hardness of examples, and are computationally expensive. In this paper, we propose a sampling strategy for hard negative mining, in which sampling directions are determined by the similarity between data examples and the margin. Our proposed method reduces the impact of noise by amplifying the dissimilarity of Softmax loss between hard examples for a more accurate model. The experimental results of image retrieval on CARS196 and CUB-200-2011 dataset demonstrate the effectiveness and superiority of our proposed method, compared to several existing state-of-the-art techniques.
References
[1]
Schroff F, Kalenichenko D, Philbin J. Facenet: A unified embedding for face recognition and clustering{C}//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 815--823.Ding, W. and Marchionini, G. 1997. A Study on Video Browsing Strategies. Technical Report. University of Maryland at College Park.
[2]
Sohn K. Improved deep metric learning with multi-class n-pair loss objective{C}//Advances in Neural Information Processing Systems. 2016: 1857--1865.
[3]
Oh Song H, Xiang Y, Jegelka S, et al. Deep metric learning via lifted structured feature embedding{C}//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016: 4004--4012.
[4]
Qian Q, Jin R, Zhu S, et al. Fine-grained visual categorization via multi-stage metric learning{C}//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015: 3716--3724.
[5]
Arandjelovic R, Gronat P, Torii A, et al. NetVLAD: CNN architecture for weakly supervised place recognition{C}//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016: 5297--5307.
[6]
Wang J, Song Y, Leung T, et al. Learning fine-grained image similarity with deep ranking{C}//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014: 1386--1393.
[7]
Hu J, Lu J, Tan Y P. Discriminative deep metric learning for face verification in the wild{C}//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014: 1875--1882.
[8]
Schultz M, Joachims T. Learning a distance metric from relative comparisons{C}//Advances in neural information processing systems. 2004: 41--48.
[9]
Yuan Y, Yang K, Zhang C. Hard-aware deeply cascaded embedding{C}//2017 IEEE International Conference on Computer Vision (ICCV). IEEE, 2017: 814--823.
[10]
Wu C Y, Manmatha R, Smola A J, et al. Sampling matters in deep embedding learning{C}//Proceedings of the IEEE International Conference on Computer Vision. 2017: 2840--2848.
[11]
Bromley J, Guyon I, LeCun Y, et al. Signature verification using a" siamese" time delay neural network{C}//Advances in neural information processing systems. 1994: 737--744.
[12]
Chopra S, Hadsell R, LeCun Y. Learning a similarity metric discriminatively, with application to face verification{C}//Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. IEEE, 2005, 1: 539--546.
[13]
Wilson D R, Martinez T R. The general inefficiency of batch training for gradient descent learning{J}. Neural Networks, 2003, 16(10): 1429--1451.
[14]
Tadmor O, Wexler Y, Rosenwein T, et al. Learning a metric embedding for face recognition using the multibatch method{J}. arXiv preprint arXiv:1605.07270, 2016.
[15]
He K, Zhang X, Ren S, et al. Deep residual learning for image recognition{C}//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770--778.
[16]
Jegou H, Douze M, Schmid C. Product quantization for nearest neighbor search{J}. IEEE transactions on pattern analysis and machine intelligence, 2011, 33(1): 117--128.
[17]
Hoffer E, Ailon N. Deep metric learning using triplet network{C}//International Workshop on Similarity-Based Pattern Recognition. Springer, Cham, 2015: 84--92.
[18]
Bell S, Bala K. Learning visual similarity for product design with convolutional neural networks{J}. ACM Transactions on Graphics (TOG), 2015, 34(4): 98.
[19]
Krause J, Stark M, Deng J, et al. 3D Object Representations for Fine-Grained Categorization{C}// 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13, ICCV workshop). IEEE, 2013.
[20]
Wah C., Branson S., Welinder P., Perona P., Belongie S. "The Caltech-UCSD Birds-200-2011 Dataset." Computation & Neural Systems Technical Report, CNS-TR-2011-001.
Index Terms
- Margin-based Sampling in Deep Metric Learning
Recommendations
Deep metric learning via group channel-wise ensemble
AbstractDeep metric learning aims at learning the distance metric for data samples by deep neural networks. Essentially, it derives an embedding space where the mappings of semantically related samples are much closer than those of irrelevant ...
Metric-based Generative Adversarial Network
MM '17: Proceedings of the 25th ACM international conference on MultimediaExisting methods of generative adversarial network (GAN) use different criteria to distinguish between real and fake samples, such as probability [9],energy [44] energy or other losses [30]. In this paper, by employing the merits of deep metric learning,...
Deep metric learning assisted by intra-variance in a semi-supervised view of learning
AbstractDeep metric learning aims to construct an embedding space where samples belonging to the same class are closely grouped together, while samples from different classes are widely separated. Many existing deep metric learning methods focus on ...
Graphical abstractDisplay Omitted
Highlights- We propose a generative boundary that improves the accuracy of generation.
- The generative boundary can balance inter-class variance and intra-class variance.
- We propose a ranking loss to learn the intra-class variance.
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
May 2019
353 pages
ISBN:9781450362788
DOI:10.1145/3335484
Copyright © 2019 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
In-Cooperation
- Shenzhen University: Shenzhen University
- Sun Yat-Sen University
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 10 May 2019
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICBDC 2019
ICBDC 2019: 2019 4th International Conference on Big Data and Computing
May 10 - 12, 2019
Guangzhou, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 61Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in