Sciweavers

Share
CVPR
2008
IEEE

Scene classification with low-dimensional semantic spaces and weak supervision

10 years 10 months ago
Scene classification with low-dimensional semantic spaces and weak supervision
A novel approach to scene categorization is proposed. Similar to previous works of [11, 15, 3, 12], we introduce an intermediate space, based on a low dimensional semantic "theme" image representation. However, instead of learning the themes in an unsupervised manner, they are learned with weak supervision, from casual image annotations. Each theme induces a probability density on the space of low-level features, and images are represented as vectors of posterior theme probabilities. This enables an image to be associated with multiple themes, even when there are no multiple associations in the training labels. An implementation is presented and compared to various existing algorithms, on benchmark datasets. 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. It is also shown to outperform unsupervised latent-space methods, with much smaller training ...
Nikhil Rasiwasia, Nuno Vasconcelos
Added 12 Oct 2009
Updated 12 Oct 2009
Type Conference
Year 2008
Where CVPR
Authors Nikhil Rasiwasia, Nuno Vasconcelos
Comments (0)
books