Learning The Discriminative Power-Invariance Trade-Off
The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.
Abstract
We investigate the problem of learning optimal descriptors for a given classification task. Many hand-crafted descriptors have been proposed in the literature for measuring visual similarity. Looking past initial differences, what really distinguishes one descriptor from another is the tradeoff that it achieves between discriminative power and invariance. Since this trade-off must vary from task to task, no single descriptor can be optimal in all situations. Our focus, in this paper, is on learning the optimal tradeoff for classification given a particular training set and prior constraints. The problem is posed in the kernel learning framework. We learn the optimal, domain-specific kernel as a combination of base kernels corresponding to base features which achieve different levels of trade-off (such as no invariance, rotation invariance, scale invariance, affine invariance, etc.) This leads to a convex optimisation problem with a unique global optimum which can be solved for efficiently. The method is shown to achieve state-of-the-art performance on the UIUC textures, Oxford flowers and Cal- tech 101 datasets.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Boyd, S., & Vandenberghe, L. (2004) · doi:10.1017/cbo9780511804441 · Cited by 56,601
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Lazebnik, S., Schmid, C., & Ponce, J. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.68 · Cited by 7,916
A performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · cited 1×
“A fundamental problem in visual classification is designing good descriptors and many successful ones have been proposed in the literature [31].”
BackgroundLearning a Similarity Metric Discriminatively, with Application to Face Verification
Chopra, S., Hadsell, R., & LeCun, Y. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.202 · Cited by 4,036
One-shot learning of object categories
Fei-Fei, L., Fergus, R., & Perona, P. (2006) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2006.79 · Cited by 3,029
Perturbation Analysis of Optimization Problems
Bonnans, J. F., & Shapiro, A. (2000) · Springer eBooks · doi:10.1007/978-1-4612-1394-9 · Cited by 2,400
Choosing Multiple Parameters for Support Vector Machines
Chapelle, O., Vapnik, V., Bousquet, O., & Mukherjee, S. (2002) · Machine Learning · doi:10.1023/a:1012450327387 · Cited by 2,206
Zhang, J., Marszałek, M., Lazebnik, S., & Schmid, C. (2007) · International Journal of Computer Vision · doi:10.1007/s11263-006-9794-4 · Cited by 1,923
Cited by
Distance Metric Learning for Large Margin Nearest Neighbor Classification
Weinberger, K. Q., & Saul, L. K. (2009) · Journal of Machine Learning Research · doi:10.5555/1577069.1577078 · Cited by 4,044
Automated Flower Classification over a Large Number of Classes
Nilsback, M.-E., & Zisserman, A. (2008) · 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing · doi:10.1109/icvgip.2008.47 · Cited by 3,442
“flowers/index.html, which was introduced in [12], with the two previous publications that have classified this dataset: Nilsback and Zisserman [12], and Varma and Ray [ 16 ].”
BackgroundMethodResultInfluentialAdapting visual category models to new domains
Saenko, K., Kulis, B., Fritz, M., & Darrell, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_16 · Cited by 2,847
“[4], [17], [3]).”
Lee, H., Grosse, R., Ranganath, R., & Ng, A. Y. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553453 · Cited by 2,412
What is the best multi-stage architecture for object recognition?
Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153
“While the best results on Caltech-101 have been obtained by combining a large number of different feature families [ 29 ], the present study concerns systems with a single feature family, hence results will be compared with other work in which a single feature family is used.”
MethodResultParkhi, O. M., Vedaldi, A., Zisserman, A., & Jawahar, C. V. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248092 · Cited by 1,533
In defense of Nearest-Neighbor based image classification
Boiman, O., Shechtman, E., & Irani, M. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587598 · Cited by 1,072
A Survey on Multi-view Learning
Xu, C., Tao, D., & Xu, C. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1304.5634 · Cited by 942
Classification using intersection kernel support vector machines is efficient
Maji, S., Berg, A. C., & Malik, J. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587630 · Cited by 940
Kernelized locality-sensitive hashing for scalable image search
Kulis, B., & Grauman, K. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459466 · Cited by 890
On feature combination for multiclass object classification
Gehler, P., & Nowozin, S. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459169 · Cited by 797
“In the application of MKL to object classification, the approach can be seen to linearly combine similarity functions between images such that the combined similarity function yields improved classification performance [8, 11, 20 ].”
MethodResultInfluentialIs that you? Metric learning approaches for face identification
Guillaumin, M., Verbeek, J., & Schmid, C. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459197 · Cited by 757
Multiple kernels for object detection
Vedaldi, A., Gulshan, V., Varma, M., & Zisserman, A. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459183 · Cited by 757
Self-citationConsistency of the group Lasso and multiple kernel learning
Bach, F. (2007) · arXiv (Cornell University) · doi:10.48550/arxiv.0707.3390 · Cited by 669
Why is Real-World Visual Object Recognition Hard?
Pinto, N., Cox, D. D., & DiCarlo, J. J. (2008) · PLoS Computational Biology · doi:10.1371/journal.pcbi.0040027 · Cited by 537
Image Classification Using Super-Vector Coding of Local Image Descriptors
Zhou, X., Yu, K., Zhang, T., & Huang, T. S. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15555-0_11 · Cited by 499
What Does Classifying More Than 10,000 Image Categories Tell Us?
Deng, J., Berg, A. C., Li, K., & Fei-Fei, L. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15555-0_6 · Cited by 486
Recognising spontaneous facial micro-expressions
Pfister, T., Li, X., Zhao, G., & Pietikainen, M. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126401 · Cited by 450
lp-Norm Multiple Kernel Learning
Kloft, M. (2011) · DepositOnce · doi:10.14279/depositonce-2978 · Cited by 412
More generality in efficient multiple kernel learning
Varma, M., & Babu, B. R. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553510 · Cited by 398
Self-citationVisual Classification With Multitask Joint Sparse Representation
Yuan, X.-T., Liu, X., & Yan, S. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2205006 · Cited by 364
Learning Discriminative Appearance-Based Models Using Partial Least Squares
Schwartz, W. R., & Davis, L. S. (2009) · 2009 XXII Brazilian Symposium on Computer Graphics and Image Processing · doi:10.1109/sibgrapi.2009.42 · Cited by 351
Multi-cue onboard pedestrian detection
Wojek, C., Walk, S., & Schiele, B. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206638 · Cited by 350
“More sophisticated feature combination schemes (e.g. [29]) may allow to improve performance more consistently based on multiple features.”
BackgroundKernelized Locality-Sensitive Hashing
Kulis, B., & Grauman, K. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.219 · Cited by 331
Visual classification with multi-task joint sparse representation
Yuan, X.-T., & Yan, S. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539967 · Cited by 303
Fast image search for learned metrics
Jain, P., Kulis, B., & Grauman, K. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587841 · Cited by 279
Multiple Kernel Learning for Visual Object Recognition: A Review
(2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.212 · Cited by 274
Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
Jayasumana, S., Hartley, R., Salzmann, M., Li, H., & Harandi, M. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.17 · Cited by 273
Fast Similarity Search for Learned Metrics
Kulis, B., Jain, P., & Grauman, K. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.151 · Cited by 256
Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels
Jayasumana, S., Hartley, R., Salzmann, M., Li, H., & Harandi, M. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2414422 · Cited by 252
Transfer learning for image classification with sparse prototype representations
Quattoni, A., Collins, M., & Darrell, T. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587637 · Cited by 252
Multiple Kernel Learning for Dimensionality Reduction
Lin, Y.-Y., Liu, T.-L., & Fuh, C.-S. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.183 · Cited by 245
Wu, J., & Rehg, J. M. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459178 · Cited by 242
“Several methods that use multiple cues outperformed our method, for example [4, 3, 30 ].”
MethodJoint learning and dictionary construction for pattern recognition
Pham, D.-S., & Venkatesh, S. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587408 · Cited by 232
“The highest recognition accuracy of 79.85% was reported in [ 31 ] which uses sophisticated low-level vision techniques and complex classifier.”
BackgroundInfluential“Who are you?” - Learning person specific classifiers from video
Sivic, J., Everingham, M., & Zisserman, A. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206513 · Cited by 223
“Rather than using a single pre-specified kernel, the kernel is a linear combination of given base kernels [3, 19 ], with each base kernel corresponding to a different feature.”
MethodInfluentialEfficient Classification for Additive Kernel SVMs
Maji, S., Berg, A. C., & Malik, J. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.62 · Cited by 217
“Index Terms—Image classification, support vector machines, efficient classifiers, additive kernels Ç”
BackgroundMulti-kernel Correlation Filter for Visual Tracking
Tang, M., & Feng, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.348 · Cited by 160
Grauman, K., & Leibe, B. (2011) · Synthesis Lectures on Artificial Intelligence and Machine Learning · doi:10.2200/s00332ed1v01y201103aim011 · Cited by 126
High-Speed Tracking with Multi-kernel Correlation Filters
Tang, M., Yu, B., Zhang, F., & Wang, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00512 · Cited by 103
Metadata
- Authors
- Varma, M., & Ray, D.
- Venue
- 2007 IEEE 11th International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2007
- Pages
- 1-8
- OpenAlex
- W2122808326
- Cited by
- 520
- References
- 47
- FWCI
- 46.53
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.