An invariant large margin nearest neighbour classifier
The k-nearest neighbour (kNN) rule is a simple and effective method for multi-way classification that is much used in Computer Vision. However, its performance depends heavily on the distance metric being employed. The recently proposed large margin nearest neighbour (LMNN) classifier [21] learns a...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2007
|
| _version_ | 1826315109751848960 |
|---|---|
| author | Kumar, MP Torr, PHS Zisserman, A |
| author_facet | Kumar, MP Torr, PHS Zisserman, A |
| author_sort | Kumar, MP |
| collection | OXFORD |
| description | The k-nearest neighbour (kNN) rule is a simple and effective method for multi-way classification that is much used in Computer Vision. However, its performance depends heavily on the distance metric being employed. The recently proposed large margin nearest neighbour (LMNN) classifier [21] learns a distance metric for kNN classification and thereby improves its accuracy. Learning involves optimizing a convex problem using semidefinite programming (SDP). We extend the LMNN framework to incorporate knowledge about invariance of the data. The main contributions of our work are three fold: (i) Invariances to multivariate polynomial transformations are incorporated without explicitly adding more training data during learning - these can approximate common transformations such as rotations and affinities; (ii) the incorporation of different regularizes on the parameters being learnt; and (Hi) for all these variations, we show that the distance metric can still be obtained by solving a convex SDP problem. We call the resulting formulation invariant LMNN (lLMNN) classifier. We test our approach to learn a metric for matching (i) feature vectors from the standard Iris dataset; and (ii) faces obtained from TV video (an episode of 'Buffy the Vampire Slayer'). We compare our method with the state of the art classifiers and demonstrate improvements. |
| first_indexed | 2024-12-09T03:20:02Z |
| format | Conference item |
| id | oxford-uuid:341e8463-a3ff-4bcd-9f56-0e90cd686772 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:20:02Z |
| publishDate | 2007 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:341e8463-a3ff-4bcd-9f56-0e90cd6867722024-11-05T15:37:34ZAn invariant large margin nearest neighbour classifierConference itemhttp://purl.org/coar/resource_type/c_5794uuid:341e8463-a3ff-4bcd-9f56-0e90cd686772EnglishSymplectic ElementsIEEE2007Kumar, MPTorr, PHSZisserman, AThe k-nearest neighbour (kNN) rule is a simple and effective method for multi-way classification that is much used in Computer Vision. However, its performance depends heavily on the distance metric being employed. The recently proposed large margin nearest neighbour (LMNN) classifier [21] learns a distance metric for kNN classification and thereby improves its accuracy. Learning involves optimizing a convex problem using semidefinite programming (SDP). We extend the LMNN framework to incorporate knowledge about invariance of the data. The main contributions of our work are three fold: (i) Invariances to multivariate polynomial transformations are incorporated without explicitly adding more training data during learning - these can approximate common transformations such as rotations and affinities; (ii) the incorporation of different regularizes on the parameters being learnt; and (Hi) for all these variations, we show that the distance metric can still be obtained by solving a convex SDP problem. We call the resulting formulation invariant LMNN (lLMNN) classifier. We test our approach to learn a metric for matching (i) feature vectors from the standard Iris dataset; and (ii) faces obtained from TV video (an episode of 'Buffy the Vampire Slayer'). We compare our method with the state of the art classifiers and demonstrate improvements. |
| spellingShingle | Kumar, MP Torr, PHS Zisserman, A An invariant large margin nearest neighbour classifier |
| title | An invariant large margin nearest neighbour classifier |
| title_full | An invariant large margin nearest neighbour classifier |
| title_fullStr | An invariant large margin nearest neighbour classifier |
| title_full_unstemmed | An invariant large margin nearest neighbour classifier |
| title_short | An invariant large margin nearest neighbour classifier |
| title_sort | invariant large margin nearest neighbour classifier |
| work_keys_str_mv | AT kumarmp aninvariantlargemarginnearestneighbourclassifier AT torrphs aninvariantlargemarginnearestneighbourclassifier AT zissermana aninvariantlargemarginnearestneighbourclassifier AT kumarmp invariantlargemarginnearestneighbourclassifier AT torrphs invariantlargemarginnearestneighbourclassifier AT zissermana invariantlargemarginnearestneighbourclassifier |