2015

Metric Learning with Adaptive Density Discrimination

Rippel, Oren, Paluri, Manohar, Dollar, Piotr et al.

Understand

Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity.

While such models offer a number of compelling benefits, it has been difficult for these to compete with modern classification algorithms in performance and even in feature extraction.
In this work, we propose a novel approach explicitly designed to address a number of subtle yet important issues which have stymied earlier DML algorithms.
It maintains an explicit model of the distributions of the different classes in representation space.

Built on

Neighbourhood components analysis
Goldberger, Jacob, Roweis, Sam, Hinton, Geoff, and Salakhutdinov, Ruslan · 2004
Earlier work this paper cites.
Learning a similarity metric discriminatively, with application to face verification
Chopra, Sumit, Hadsell, Raia, and LeCun, Yann · 2005
Earlier work this paper cites.
Metric learning by collapsing classes
Globerson, Amir and Roweis, Sam T · 2006
Earlier work this paper cites.
Dimensionality reduction by learning an invariant mapping
Hadsell, Raia, Chopra, Sumit, and Lecun, Yann · 2006
Earlier work this paper cites.
K-means++: The advantages of careful seeding
Arthur, David and Vassilvitskii, Sergei · 2007
Earlier work this paper cites.
Learning a nonlinear embedding by preserving class neighbourhood structure
Salakhutdinov, Ruslan and Hinton, Geoffrey E · 2007
Earlier work this paper cites.
Automated flower classification over a large number of classes
Nilsback, M-E. and Zisserman, A · 2008
Earlier work this paper cites.
Visualizing high-dimensional data using t-sne
van der Maaten, L.J.P. and Hinton, G.E · 2008
Earlier work this paper cites.
Distance metric learning for large margin nearest neighbor classification
Weinberger, Kilian Q. and Saul, Lawrence K · 2009
Earlier work this paper cites.
Deep supervised t-distributed embedding
Min, Martin Renqiang, van der Maaten, Laurens, Yuan, Zineng, Bonner, Anthony J., and Zhang, Zhaolei · 2010
Earlier work this paper cites.
Attribute learning in large-scale datasets
Russakovsky, Olga and Fei-Fei, Li · 2010
Earlier work this paper cites.

Similar

Novel dataset for fine-grained image categorization
Khosla, Aditya, Jayadevaprakash, Nityananda, Yao, Bangpeng, and Fei-Fei, Li · 2011
Cited alongside, same era.
Hamming distance metric learning
Norouzi, Mohammad, Fleet, David, and Salakhutdinov, Ruslan R · 2012
Cited alongside, same era.
Cats and dogs
Parkhi, O. M., Vedaldi, A., Zisserman, A., and Jawahar, C. V · 2012
Cited alongside, same era.
Learning hierarchical similarity metrics
Verma, Nakul, Mahajan, Dhruv, Sellamanickam, Sundararajan, and Nair, Vinod · 2012
Cited alongside, same era.
Efficient object detection and segmentation for fine-grained recognition
Angelova, Anelia and Zhu, Shenghuo · 2013
Cited alongside, same era.
Decaf: A deep convolutional activation feature for generic visual recognition
Donahue, Jeff, Jia, Yangqing, Vinyals, Oriol, Hoffman, Judy, Zhang, Ning, Tzeng, Eric, and Darrell, Trevor · 2013
Cited alongside, same era.
Fine-grained categorization by alignments
Gavves, E., Fernando, B., Snoek, C. G. M., Smeulders, A. W. M., and Tuytelaars, T · 2013
Cited alongside, same era.
Distance-based image classification: Generalizing to new classes at near zero cost
Mensink, Thomas, Verbeek, Jakob, Perronnin, Florent, and Csurka, Gabriela · 2013
Cited alongside, same era.
Benchmarking large-scale fine-grained categorization
Angelova, Anelia and Long, Philip M · 2014
Cited alongside, same era.
Generalized max pooling
Murray, Naila and Perronnin, Florent · 2014
Cited alongside, same era.

Then

Cnn features off-the-shelf: An astounding baseline for recognition
Sharif Razavian, Ali, Azizpour, Hossein, Sullivan, Josephine, and Carlsson, Stefan · 2014
Later among the works it cites.
Learning fine-grained image similarity with deep ranking
Wang, Jiang, Song, Yang, Leung, Thomas, Rosenberg, Chuck, Wang, Jingbin, Philbin, James, Chen, Bo, and Wu, Ying · 2014
Later among the works it cites.
Local alignments for fine-grained categorization
Gavves, Efstratios, Fernando, Basura, Snoek, CeesG.M., Smeulders, ArnoldW.M., and Tuytelaars, Tinne · 2015
Closest in time.
Batch normalization: Accelerating deep network training by reducing internal covariate shift
Ioffe, Sergey and Szegedy, Christian · 2015
Closest in time.
Fine-grained visual categorization via multi-stage metric learning
Qian, Qi, Jin, Rong, Zhu, Shenghuo, and Lin, Yuanqing · 2015
Closest in time.
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, Olga, Deng, Jia, Su, Hao, Krause, Jonathan, Satheesh, Sanjeev, Ma, Sean, Huang, Zhiheng, Karpathy, Andrej, Khosla, Aditya, Bernstein, Michael, Berg, Alexander C., and Fei-Fei, Li · 2015
Closest in time.
Facenet: A unified embedding for face recognition and clustering
Schroff, Florian, Kalenichenko, Dmitry, and Philbin, James · 2015
Closest in time.
Scalable bayesian optimization using deep neural networks
Snoek, Jasper, Rippel, Oren, Swersky, Kevin, Kiros, Ryan, Satish, Nadathur, Sundaram, Narayanan, Patwary, Md. Mostofa Ali, Prabhat, and Adams, Ryan P · 2015
Closest in time.
Going deeper with convolutions
Szegedy, Christian, Liu, Wei, Jia, Yangqing, Sermanet, Pierre, Reed, Scott, Anguelov, Dragomir, Erhan, Dumitru, Vanhoucke, Vincent, and Rabinovich, Andrew · 2015
Closest in time.
Hyper-class augmented and regularized deep learning for fine-grained image classification
Xie, Saining, Yang, Tianbao, Wang, Xiaoyu, and Lin, Yuanqing · 2015
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…