Generative versus discriminative methods for object recognition

Date

2005-06-25

Author

Ulusoy, İlkay

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

209
views

0
downloads

Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the distribution of the image features is modelled. Generative and discriminative methods have very different characteristics, as well as complementary strengths and weaknesses. In this paper we introduce new generative and discriminative models for object detection and classification based on weakly labelled training data. We use these models to illustrate the relative merits of the two approaches in the context of a data set of widely varying images of non-rigid objects (animals). Our results support the assertion that neither approach alone will be sufficient for large scale object recognition, and we discuss techniques for combining them.

Subject Keywords

Object recognition, Machine learning, Computer vision, Large-scale systems, Character generation, Training data, Predictive models, Object detection, Context modeling, Animals

URI

https://hdl.handle.net/11511/37262

DOI

https://doi.org/10.1109/cvpr.2005.167

Conference Name

Conference on Computer Vision and Pattern Recognition

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Comparison of generative and discriminative techniques for object detection and classification Ulusoy, İlkay (2004-01-01) Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the distribution of the image features is modelled. Generative and discriminative methods have very different characteristics, as well as complementary strengths and weaknesses. In this chapter we introduce new generative and discriminative models for object detection and classification based on weakly labelled training data. We use thes...
Rescoring detections based on contextual scores in object detection Zorlu, Ersan Vural; Akbaş, Emre; Department of Computer Engineering (2019) To detect objects in an image, current state-of-the-art object detectors firstly definecandidate object locations, and then classify each of them into one of the predefinedcategories or as background. They do so by using the visual features extracted locallyfrom the candidate locations; omitting the rich contextual information embedded inthe whole image. Contextual information can be utilized to complement the informa-tion extracted locally and thereby to improve object detection accuracy. Researchershave p...
Scale invariant representation of 2 5D data AKAGUNDUZ, Erdem; ULUSOY PARNAS, İLKAY; BOZKURT, Nesli; Halıcı, Uğur (2007-06-13) In this paper, a scale and orientation invariant feature representation for 2.5D objects is introduced, which may be used to classify, detect and recognize objects even under the cases of cluttering and/or occlusion. With this representation a 2.5D object is defined by an attributed graph structure, in which the nodes are the pit and peak regions on the surface. The attributes of the graph are the scales, positions and the normals of these pits and peaks. In order to detect these regions a "peakness" (or pi...
Individualism and collectivism in a model and scale of balanced differentiation and integration İmamoğlu, Emine Olcay (1998-01-01) To discern some key features of individualistic and collectivistic human model conceptualizations within a parsimonious framework, the author proposed a model based on the notion that balancing the basic orientations for self-developmental differentiation (individuation) and interrelational integration (interrelatedness) promotes optimal development. The Balanced Differentiation and Integration Scale (BDIS) and the Balanced Orientation Scale (BOS), which was developed as a validity check for the BDIS, were ...
Continuous dimensionality characterization of image structures Felsberg, Michael; Kalkan, Sinan; Kruger, Norbert (Elsevier BV, 2009-05-04) Intrinsic dimensionality is a concept introduced by statistics and later used in image processing to measure the dimensionality of a data set. In this paper, we introduce a continuous representation of the intrinsic dimension of an image patch in terms of its local spectrum or, equivalently, its gradient field. By making use of a cone structure and barycentric co-ordinates, we can associate three confidences to the three different ideal cases of intrinsic dimensions corresponding to homogeneous image patche...

Citation Formats

İ. Ulusoy, “Generative versus discriminative methods for object recognition,” presented at the Conference on Computer Vision and Pattern Recognition, San Diego, CA, 2005, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/37262.