Learning Equivariant Structured Output SVM Regressors - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

Learning Equivariant Structured Output SVM Regressors


Equivariance and invariance are often desired properties of a computer vision system. However, currently available strategies generally rely on virtual sampling, leaving open the question of how many samples are necessary, on the use of invariant feature representations, which can mistakenly discard information relevant to the vision task, or on the use of latent variable models, which result in non-convex training and expensive inference at test time. We propose here a generalization of structured output SVM regressors that can incorporate equivariance and invariance into a convex training procedure, enabling the incorporation of large families of transformations, while maintaining optimality and tractability. Importantly, test time inference does not require the estimation of latent variables, resulting in highly efficient objective functions. This results in a natural formulation for treating equivariance and invariance that is easily implemented as an adaptation of off-the-shelf optimization software, obviating the need for ad hoc sampling strategies. Theoretical results relating to vicinal risk, and experiments on challenging aerial car and pedestrian detection tasks show the effectiveness of the proposed solution.
Fichier principal
Vignette du fichier
vedaldi11a.pdf (447.85 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00855739 , version 1 (31-01-2014)



Andrea Vedaldi, Matthew B. Blaschko, Andrew Zisserman. Learning Equivariant Structured Output SVM Regressors. International Conference on Computer Vision, Nov 2011, Barcelona, Spain. pp.959-966, ⟨10.1109/ICCV.2011.6126339⟩. ⟨hal-00855739⟩
197 View
219 Download



Gmail Facebook Twitter LinkedIn More