Deformable Classifiers

12/18/2017
by   Jiajun Shen, et al.
0

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.

READ FULL TEXT

page 3

page 8

page 9

page 10

page 12

page 13

page 14

page 15

research
03/19/2020

Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition

Object pose increases interclass object variance which makes object reco...
research
11/29/2021

Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes

Machine learning has been widely adopted in many domains, including high...
research
05/22/2018

Deformable Part Networks

In this paper we propose novel Deformable Part Networks (DPNs) to learn ...
research
07/13/2018

Learning-based Natural Geometric Matching with Homography Prior

Geometric matching is a key step in computer vision tasks. Previous lear...
research
12/14/2016

Defining the Pose of any 3D Rigid Object and an Associated Distance

The pose of a rigid object is usually regarded as a rigid transformation...
research
04/02/2018

Confidence from Invariance to Image Transformations

We develop a technique for automatically detecting the classification er...
research
06/24/2022

Deformable CNN and Imbalance-Aware Feature Learning for Singing Technique Classification

Singing techniques are used for expressive vocal performances by employi...

Please sign up or login with your details

Forgot password? Click here to reset