SVCL - Saliency

Home People Research Publications Demos

News Jobs Prospective
Students About Internal

Discriminant Saliency Detection

Biological vision systems rely on saliency mechanisms to cope with the complexity of visual perception. Rather than sequentially scanning all possible locations of a scene for the occurrence of events of possible interest, these events simply "pop-out" from the scene background. In this way, saliency enables the efficient allocation of perceptual resources and increases the robustness of recognition in highly cluttered environments.

In the computer vision literature, computational definitions of saliency have tended to rely on "universal" saliency principles that result in the detection of generic visual attributes such as edges, contours, corners, parallelism, etc. This lacks both the flexibility and adaptability of biological saliency. This project explores a definition of saliency which is directly grounded on recognition, and argues for saliency detectors that are learned in a discriminant fashion. It has shown that it is possible to learn saliency detectors that have low complexity, are scalable to large scale recognition problems, are compatible with existing models or early biological vision, and can be easily adapted for the recognition of diverse visual concepts.

Selected Publications:

Discriminant Saliency for Visual Recognition from Cluttered Scenes
Dashan Gao and Nuno Vasconcelos,
Proceedings of Neural Information Processing Systems (NIPS),
Vancouver, Canada, 2004. [ps][pdf].

An Experimental Comparison of Three Guiding Principles for the Detection of Salient Image Locations: Stability, Complexity, and Discrimination
Dashan Gao and Nuno Vasconcelos,
Proceedings of The 3rd International Workshop on Attention and Performance in Computational Vision (WAPCV),
San Diego, June 2005. [ps] [pdf].

Integrated learning of saliency, complex features, and objection detectors from cluttered scenes
Dashan Gao and Nuno Vasconcelos,
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
San Diego, June 2005. [ps] [pdf] (A longer version is available [ps] [pdf]).

Demos/
Results:

Extensive results of discriminant saliency on object and texture databases

slides from NIPS 04

Code:

(Last updated on 05/24/2006) The compiled binaries for discriminant saliency detection is available here. Read the License conditions before download. See the README for the usage of the programs.
Installation of ImageMagick is needed for running the code. It can be downloaded free here.

Contact: Dashan Gao, Nuno Vasconcelos

Home	People	Research	Publications	Demos

News	Jobs	Prospective Students	About	Internal

Discriminant Saliency Detection

Biological vision systems rely on saliency mechanisms to cope with the complexity of visual perception. Rather than sequentially scanning all possible locations of a scene for the occurrence of events of possible interest, these events simply "pop-out" from the scene background. In this way, saliency enables the efficient allocation of perceptual resources and increases the robustness of recognition in highly cluttered environments. In the computer vision literature, computational definitions of saliency have tended to rely on "universal" saliency principles that result in the detection of generic visual attributes such as edges, contours, corners, parallelism, etc. This lacks both the flexibility and adaptability of biological saliency. This project explores a definition of saliency which is directly grounded on recognition, and argues for saliency detectors that are learned in a discriminant fashion. It has shown that it is possible to learn saliency detectors that have low complexity, are scalable to large scale recognition problems, are compatible with existing models or early biological vision, and can be easily adapted for the recognition of diverse visual concepts.
Selected Publications:	Discriminant Saliency for Visual Recognition from Cluttered Scenes Dashan Gao and Nuno Vasconcelos, Proceedings of Neural Information Processing Systems (NIPS), Vancouver, Canada, 2004. [ps][pdf]. An Experimental Comparison of Three Guiding Principles for the Detection of Salient Image Locations: Stability, Complexity, and Discrimination Dashan Gao and Nuno Vasconcelos, Proceedings of The 3rd International Workshop on Attention and Performance in Computational Vision (WAPCV), San Diego, June 2005. [ps] [pdf]. Integrated learning of saliency, complex features, and objection detectors from cluttered scenes Dashan Gao and Nuno Vasconcelos, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, June 2005. [ps] [pdf] (A longer version is available [ps] [pdf]).
Demos/ Results:	Extensive results of discriminant saliency on object and texture databases slides from NIPS 04
Code:	(Last updated on 05/24/2006) The compiled binaries for discriminant saliency detection is available here. Read the License conditions before download. See the README for the usage of the programs. Installation of ImageMagick is needed for running the code. It can be downloaded free here.
Contact:	Dashan Gao, Nuno Vasconcelos