Unsupervised Learning of Models for Recognition

  title={Unsupervised Learning of Models for Recognition},
  author={Markus Weber and Max Welling and Pietro Perona},
We present a method to learn object class models from unlabeled and unsegmented cluttered scenes for the purpose of visual object recognition. We focus on a particular type of model where objects are represented as flexible constellations of rigid parts (features). The variability within a class is represented by a joint probability density function (pdf) on the shape of the constellation and the output of part detectors. In a first stage, the method automatically identifies distinctive parts… 
Unsupervised learning of models for object recognition
A method to learn object class models from unlabeled and unsegmented cluttered cluttered scenes for the purpose of visual object recognition achieves very good classification results on human faces, cars, leaves, handwritten letters, and cartoon characters.
Towards automatic discovery of object categories
A method to learn heterogeneous models of object classes for visual recognition that automatically identifies distinctive features in the training set and learns the set of model parameters using expectation maximization.
Object class recognition by unsupervised scale-invariant learning
The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).
Statistical part-based models for object category recognition
A new method to learn statistical part-based structure models for object category recognition in a supervised manner that provides both successful classification and localization of the object within the image.
A sparse object category model for efficient learning and exhaustive recognition
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semi-supervised manner: the model is learnt from example images containing category
Learning of Graphical Models and Efficient Inference for Object Class Recognition
This work focuses on learning graphical models of object classes from arbitrary instances of objects by combining statistical local part detection with relations between object parts in a probabilistic network and shows performance equal or superior to dedicated face recognition approaches.
A Sparse Object Category Model for Efficient Learning and Complete Recognition
A parts and structure model for object category recognition that can be learnt efficiently and in a weakly-supervised manner, bypassing the need for feature detectors, to give the globally optimal match within a query image.
Recognition by Probabilistic Hypothesis Construction
A probabilistic framework for recognizing objects in images of cluttered scenes, learned from a single training image and modeled by the visual appearance of a set of features, and their position with respect to a common reference frame is presented.
Efficient Unsupervised Learning for Localization and Detection in Object Categories
A novel method for learning templates for recognition and localization of objects drawn from categories using a generative model that allows learning to be orders of magnitude faster than previous approaches while incorporating many more features.
Multiple Object Class Detection with a Generative Model
The performance of the proposed multi-object class detection approach is competitive to state of the art approaches dedicated to a single object class recognition problem.


A Probabilistic Approach to Object Recognition Using Local Photometry and Global Geometry
A simplified model of a deformable object class is introduced and the optimal detector for this model is derived, which is not realizable except under special circumstances (independent part positions).
Recognition of planar object classes
  • M. Burl, P. Perona
  • Computer Science
    Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1996
We present a new framework for recognizing planar object classes, which is based on local feature detectors and a probabilistic model of the spatial arrangement of the features. The allowed object
Locating Objects of Varying Shape Using Statistical Feature Detectors
This paper describes an approach for generating starting points automatically given no prior knowledge of the pose of the target(s) in the image, which relies upon choosing a suitable set of features, candidates for which can be found in theimage, which is demonstrated for two different image interpretation problems.
Distortion Invariant Object Recognition in the Dynamic Link Architecture
An object recognition system based on the dynamic link architecture, an extension to classical artificial neural networks (ANNs), is presented and the implementation on a transputer network achieved recognition of human faces and office objects from gray-level camera images.
A Computational Model for Visual Selection
The model was not conceived to explain brain functions, but it does cohere with evidence about the functions of neurons in V1 and V2, such as responses to coarse or incomplete patterns and to scale and translation invariance in IT.
Face Recognition Using Active Appearance Models
This paper demonstrates the use of the AAM's efficient iterative matching scheme for image interpretation, which allows identity information to be decoupled from other variation, allowing evidence of identity to be integrated over a sequence.
Deformable Templates for Face Recognition
  • A. Yuille
  • Computer Science
    Journal of Cognitive Neuroscience
  • 1991
We describe an approach for extracting facial features from images and for determining the spatial organization between these features using the concept of a deformable template. This is a
Finding faces in cluttered scenes using random labeled graph matching
An algorithm for locating quasi-frontal views of human faces in cluttered scenes is presented and it is found that it is invariant with respect to translation, rotation, and scale and can handle partial occlusions of the face.
Face Localization via Shape Statistics
A face localization system is proposed in which local detectors are coupled with a statistical model of the spatial arrangement of facial features to yield robust performance and constellations are formed from these.
Probabilistic affine invariants for recognition
  • T. Leung, M. Burl, P. Perona
  • Mathematics
    Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)
  • 1998
Under the assumption that the feature positions of a planar object can be modeled using a jointly Gaussian density, the joint density over the corresponding set of affine coordinates is derived.