Abstract
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 the themes without supervision. We report satisfactory categorization performances on a large set of 13 categories of complex scenes.
Keywords
CategorizationTheme (computing)Computer scienceArtificial intelligenceSet (abstract data type)Natural (archaeology)Bayesian probabilityMachine learningImage (mathematics)Unsupervised learningPattern recognition (psychology)Natural language processingGeography
Affiliated Institutions
Related Publications
Discovering objects and their location in images
We seek to discover the object categories depicted in a set of unlabelled images. We achieve this using a model developed in the statistical text literature: probabilistic Laten...
Learning to Align from Scratch
Unsupervised joint alignment of images has been demonstrated to improve performance on recognition tasks such as face verification. Such alignment reduces undesired variability ...
SUN database: Large-scale scene recognition from abbey to zoo
Scene categorization is a fundamental problem in computer vision. However, scene understanding research has been constrained by the limited scope of currently-used databases whi...
Deep Clustering for Unsupervised Learning of Visual Features
Clustering is a class of unsupervised learning methods that has been extensively applied and studied in computer vision. Little work has been done to adapt it to the end-to-end ...
Dynamic scene understanding: The role of orientation features in space and time in scene classification
Natural scene classification is a fundamental challenge in computer vision. By far, the majority of studies have limited their scope to scenes from single image stills and there...
Publication Info
- Year
- 2005
- Type
- article
- Volume
- 2
- Pages
- 524-531
- Citations
- 3589
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
3589
OpenAlex
Cite This
Li Fei-Fei,
Pietro Perona
(2005).
A Bayesian Hierarchical Model for Learning Natural Scene Categories.
, 2
, 524-531.
https://doi.org/10.1109/cvpr.2005.16
Identifiers
- DOI
- 10.1109/cvpr.2005.16