Deformable classifiers
From MaRDI portal
Abstract: Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training deformable classifiers, where latent transformation variables are introduced, and a transformation of the object image to a reference instantiation is computed in terms of the classifier output, separately for each class. The classifier outputs for each class, after transformation, are compared to yield the final decision. As a by-product of the classification this yields a transformation of the input object to a reference pose, which can be used for downstream tasks such as the computation of object support. We apply a two-step training mechanism for our framework, which alternates between optimizing over the latent transformation variables and the classifier parameters to minimize the loss function. We show that multilayer perceptrons, also known as deep networks, are well suited for this approach and achieve state of the art results on the rotated MNIST and the Google Earth dataset, and produce competitive results on MNIST and CIFAR-10 when training on smaller subsets of training data.
Recommendations
Cites work
- Computational anatomy: an emerging discipline
- Geodesic shooting for computational anatomy
- scientific article; zbMATH DE number 49408 (Why is no real title available?)
- scientific article; zbMATH DE number 523032 (Why is no real title available?)
- Principal warps: thin-plate splines and the decomposition of deformations
- Shapes and diffeomorphisms
- Towards a Coherent Statistical Framework for Dense Deformable Template Estimation
This page was built for publication: Deformable classifiers
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3121208)
