Kernelizing Spatially Consistent Visual Matches for Fine-Grained Classification - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Kernelizing Spatially Consistent Visual Matches for Fine-Grained Classification

(1, 2, 3) , (2, 3) , (4) , (5, 3, 6)
1
2
3
4
5
6

Abstract

This paper introduces a new image representation relying on the spatial pooling of geometrically consistent visual matches. We therefore introduce a new match kernel based on the in- verse rank of the shared nearest neighbors combined with local geometric constraints. To avoid over tting and reduce processing costs, the dimensionality of the resulting over- complete representation is further reduced by hierarchically pooling the raw consistent matches according to their spa- tial position in the training images. The nal image repre- sentation is obtained by concatenating the resulting feature vectors at several resolutions. Learning from these represen- tations using a logistic regression classi er is shown to pro- vide excellent ne-grained classi cation performances out- performing the results reported in the literature on several classi cation tasks.
Not file

Dates and versions

hal-01145988 , version 1 (27-04-2015)

Identifiers

Cite

Valentin Leveau, Alexis Joly, Olivier Buisson, Patrick Valduriez. Kernelizing Spatially Consistent Visual Matches for Fine-Grained Classification. ICMR: International Conference on Multimedia Retrieval, Jun 2015, Shangai, China. pp.155-162, ⟨10.1145/2671188.2749328⟩. ⟨hal-01145988⟩
279 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More