Similarity estimation techniques from rounding algorithms
STOC '02 Proceedings of the thiry-fourth annual ACM symposium on Theory of computing
Recognition with Local Features: the Kernel Recipe
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Learning over sets using kernel principal angles
The Journal of Machine Learning Research
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
A near-linear constant-factor approximation for euclidean bipartite matching?
SCG '04 Proceedings of the twentieth annual symposium on Computational geometry
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Unsupervised Learning of Categories from Sets of Partially Matching Image Features
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
The Pyramid Match Kernel: Efficient Learning with Sets of Features
The Journal of Machine Learning Research
Matching sets of features for efficient retrieval and recognition
Matching sets of features for efficient retrieval and recognition
| Hi-index | 0.00 |
It is often useful to represent a single example by a set of the local features that comprise it. However, this representation poses a challenge to many conventional learning techniques, since sets may vary in cardinality and the elements are unordered. To compare sets of features, researchers often resort to solving for the least-cost correspondences, but this is computationally expensive and becomes impractical for large set sizes. We have developed a general approximate matching technique called the pyramid match that measures partial match similarity in time linear in the number of feature vectors per set. The matching forms a Mercer kernel, making it valid for use in many existing kernel-based learning methods. We have demonstrated the approach for various learning tasks in vision and text processing, and find that it is accurate and significantly more efficient than previous approaches.