A Bayesian hierarchical model for learning natural scene categories

@article{FeiFei2005ABH,
  title={A Bayesian hierarchical model for learning natural scene categories},
  author={Li Fei-Fei and Pietro Perona},
  journal={2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)},
  year={2005},
  volume={2},
  pages={524-531 vol. 2}
}
  • Li Fei-Fei, P. Perona
  • Published 20 June 2005
  • Computer Science
  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
We propose a novel approach to learn and recognize natural scene categories. Unlike previous work, it does not require experts to annotate the training set. We represent the image of a scene by a collection of local regions, denoted as codewords obtained by unsupervised learning. Each region is represented as part of a "theme". In previous work, such themes were learnt from hand-annotations of experts, while our method learns the theme distributions as well as the codewords distribution over… 
Final Project Report : Unsupervised Learning of Scene Categories
We present the Hierarchical Latent Dirichlet Allocation (hLDA) for organizing a collection of scene images into a hierarchy in unsupervised fashion. The bag of visual words model with spatial
Category Constrained Learning Model for Scene Classification
TLDR
A novel model, named Category Constraint-Latent Dirichlet Allocation (CC-LDA), to learn and recognize natural scene category and can do discrimination without combined additional classifier, during the same time of getting topic representation.
Learning hierarchical models of scenes, objects, and parts
TLDR
Applied to a database of images of isolated objects, the sharing of parts among objects improves detection accuracy when few training examples are available and this hierarchical probabilistic model is extended to scenes containing multiple objects.
Natural Scene Classification Based on Integrated Topic Simplex
TLDR
The experiments have shown the model outperforms latent-space methods with less training data, and each category is represented in a different topics simplex, which correlates well with human scene understanding.
Unsupervised Learning of Categorical Segments in Image Collections
TLDR
A unified framework for carrying out segmentation and recognition simultaneously and without supervision is proposed, which may be used for learning new categories, detecting/classifying objects, and segmenting images, without using expensive human annotation.
Unsupervised Learning of Categorical Segments in Image Collections
TLDR
A unified framework for carrying out segmentation and recognition simultaneously and without supervision is proposed, which may be used for learning new categories, detecting/classifying objects, and segmenting images, without using expensive human annotation.
Scene classification with low-dimensional semantic spaces and weak supervision
TLDR
It is shown that the proposed low dimensional representation correlates well with human scene understanding, and is able to learn theme co-occurrences without explicit training, and to outperform unsupervised latent-space methods, with much smaller training complexity.
Learning discriminative visual dictionary for natural scene categorization
TLDR
The goal of this paper is to show how to achieve the best performance by learning a semi-supervised discriminative dictionary, and to provide theoretical and empirical insight into the remarkable performance.
Scene and place recognition using a hierarchical latent topic model
TLDR
A novel latent topic model is proposed to learn and recognize scenes and places and it is shown that the proposed HLDA method performs better than other counterparts in terms of accuracy and robustness with the variation of illumination conditions, perspectives, and scales.
A Thousand Words in a Scene
This paper presents a novel approach for visual scene modeling and classification, investigating the combined use of text modeling methods and local invariant features. Our work attempts to elucidate
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 23 REFERENCES
A Semantic Typicality Measure for Natural Scene Categorization
TLDR
An approach to categorize real-world natural scenes based on a semantic typicality measure that represents the diversity of the given image categories as well as the ambiguity in human judgment of image categorization.
Sharing features: efficient boosting procedures for multiclass object detection
TLDR
A multi-class boosting procedure (joint boosting) is presented that reduces both the computational and sample complexity, by finding common features that can be shared across the classes.
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
  • A. Oliva, A. Torralba
  • Mathematics, Computer Science
    International Journal of Computer Vision
  • 2004
TLDR
The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.
Saliency, Scale and Image Description
TLDR
A multiscale algorithm for the selection of salient regions of an image is introduced and its application to matching type problems such as tracking, object recognition and image retrieval is demonstrated.
Image classification for content-based indexing
TLDR
The goal is to combine multiple two-class classifiers into a single hierarchical classifier, and it is demonstrated that a small vector quantizer can be used to model the class-conditional densities of the features, required by the Bayesian methodology.
Indoor-outdoor image classification
  • M. Szummer, Rosalind W. Picard
  • Computer Science
    Proceedings 1998 IEEE International Workshop on Content-Based Access of Image and Video Database
  • 1998
TLDR
This work systematically studied the features of: histograms in the Ohta color space; multiresolution, simultaneous autoregressive model parameters; and coefficients of a shift-invariant DCT to show how high-level scene properties can be inferred from classification of low-level image features.
Latent Dirichlet Allocation
We propose a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams [6], and
Rapid natural scene categorization in the near absence of attention
TLDR
It is reported that subjects can rapidly detect animals or vehicles in briefly presented novel natural scenes while simultaneously performing another attentionally demanding task, and some visual tasks associated with “high-level” cortical areas may proceed in the near absence of attention.
Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons
TLDR
A unified model to construct a vocabulary of prototype tiny surface patches with associated local geometric and photometric properties, represented as a set of linear Gaussian derivative filter outputs, under different lighting and viewing conditions is provided.
Object recognition from local scale-invariant features
  • D. Lowe
  • Mathematics, Computer Science
    Proceedings of the Seventh IEEE International Conference on Computer Vision
  • 1999
TLDR
Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
...
1
2
3
...