Abstract
Descriptors extracted from deep neural networks have been shown to be very discriminative, for example networks such as those trained on the large, very general ImageNet dataset have been used to extract descriptors robust for a variety of image classification tasks. Such retrieval systems utilize feature locality, for example Approximate Nearest Neighbour. Our goal is to use such descriptors as part of a large scale object instance recognition and retrieval system. We propose using deep nonlinear metric learning on Convolutional Neural Networks to learn features with good locality. In particular we worked with two related methods, Neighborhood Components Analysis (NCA) and the related Mean square Error’s Gradient Minimization (MEGM).
We utilize a nonlinear form of MEGM as an alternative to NCA and propose some stochastic sampling methods to apply these (normally batch) methods to larger datasets with minibatch Stochastic Gradient Descent (SGD). On a larger scale we found the methods difficult to train, failing to converge or generalizing very badly depending on training method or parameters. This led us to go back to a smaller dataset and examine the factors which lead to good generalization with this form of training.
We found on a small subset of the RGB-D dataset, surprisingly stochastic sampling methods generalized much better with small batch sizes, which acted as a form of regularization. When trained with larger batches, or as a full batch, the dataset was overfit. Given the correct parameters, descriptors extracted performed well at the Nearest Neighbour task and exceeded the performance of those extracted by applying standard supervised training.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 1–9 (2012)
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks. arXiv preprint, 1–16 (2013)
Masci, J., Giusti, A., Cirean, D., Fricout, G., Schmidhuber, J.: A Fast Learning Algorithm for Image Segmentation with Max-Pooling Convolutional Networks. arXiv preprint (2013)
Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN Features off-the-shelf: an Astounding Baseline for Recognition. arXiv preprint arXiv:1403.6382 (2014)
Donahue, J., Jia, Y., Vinyals, O.: Decaf: A deep convolutional activation feature for generic visual recognition. In: International Conference in Machine Learning, vol. 32 (2014)
Socher, R.: ImageNet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)
Dosovitskiy, A., Springenberg, J., Brox, T.: Unsupervised feature learning by augmenting single images. arXiv preprint arXiv:1312.5242, 1–7 (2013)
Lowe, D.G.: Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision 60, 91–110 (2004)
Fischer, P., Dosovitskiy, A., Brox, T.: Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT, 1–10 (2014)
Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality Reduction by Learning an Invariant Mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), vol. 2, pp. 1735–1742 (2006)
Min, M.R., Stanley, D., Yuan, Z.: Large-Margin kNN Classification Using a Deep Encoder Network. In: Ninth IEEE International Conference on Data Mining, ICDM 2009 (2009)
Kostinger, M., Hirzer, M.: Large scale metric learning from equivalence constraints. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2012)
Salakhutdinov, R., Hinton, G.: Learning a nonlinear embedding by preserving class neighbourhood structure. In: AI and Statistics (2007)
Weston, J.: Deep Learning via Semi-Supervised Embedding (2009)
Min, M., Maaten, L.: Deep supervised t-distributed embedding. In: Proceedings of the 27th International Conference on Machine Learning, ICML 2010 (2010)
Mensink, T., Verbeek, J., Perronnin, F., Csurka, G.: Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 488–501. Springer, Heidelberg (2012)
Zaidi, N.A., Squire, D.M., Suter, D.: A gradient-based metric learning algorithm for k-NN classifiers. In: Li, J. (ed.) AI 2010. LNCS, vol. 6464, pp. 194–203. Springer, Heidelberg (2010)
Oneat, D.T.: Fast low-rank metric learning. Masters Thesis, University of Edinburgh (2011)
Goldberger, J., Roweis, S., Hinton, G., Salakhutdinov, R.: Neighbourhood components analysis. Advances in Neural Information Processing Systems 17 (2004)
Garcia, V., Debreuve, E., Barlaud, M.: Fast k nearest neighbor search using GPU. In: 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2, pp. 1–6. IEEE (2008)
Springenberg, J., Riedmiller, M.: Improving Deep Neural Networks with Probabilistic Maxout Units. arXiv preprint arXiv:1312.6116, 1–9 (2013)
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors, 1–18 (2012)
Mensink, T., Verbeek, J., Perronnin, F., Csurka, G.: Large Scale Metric Learning for Distance-Based Image Classification (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Batchelor, O., Green, R. (2014). Object Recognition by Stochastic Metric Learning. In: Dick, G., et al. Simulated Evolution and Learning. SEAL 2014. Lecture Notes in Computer Science, vol 8886. Springer, Cham. https://doi.org/10.1007/978-3-319-13563-2_67
Download citation
DOI: https://doi.org/10.1007/978-3-319-13563-2_67
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13562-5
Online ISBN: 978-3-319-13563-2
eBook Packages: Computer ScienceComputer Science (R0)