1 / 19

Saliency Aggregation: A Data-driven Approach

Saliency Aggregation: A Data-driven Approach. Long Mai Yuzhen Niu Feng Liu Department of Computer Science, Portland State University Portland, OR, 97207 USA. Outline. Introduction Saliency Aggregation Experiments Conclusion. Introduction. T wo major observations

benjy
Télécharger la présentation

Saliency Aggregation: A Data-driven Approach

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Saliency Aggregation: A Data-driven Approach Long Mai YuzhenNiuFeng Liu Department of Computer Science, Portland State University Portland, OR, 97207 USA

  2. Outline • Introduction • Saliency Aggregation • Experiments • Conclusion

  3. Introduction • Two major observations • Different methods perform differently in saliency analysis. • The performance of a saliency analysis method varies with individual images.

  4. Introduction

  5. Introduction • Aggregation advantages • Considers the performance gaps among individual saliency analysis methods and better determines their contribution in aggregation. • Considers that the performance of each individual saliency analysis method varies over images and is able to customize an appropriate aggregation model to each input image.

  6. Saliency Aggregation • Standard Saliency Aggregation • Given a set of m saliency maps {Si || 1 ≤ i ≤ m} computed from an image I. • The aggregated saliency value S(p) at pixel p of I • Three different options for the function ζ

  7. Saliency Aggregation

  8. Saliency Aggregation • Pixel-wise Aggregation • Associates each pixel p with a feature vector • Using logistic model to model the posterior probability

  9. Saliency Aggregation • Aggregation using Conditional Random Field • Model each pixel as a node. • The saliency label of each pixel depends not only on its feature vector, but also the labels of neighboring pixels. • The interactions within the pixels also depend on the features.

  10. Saliency Aggregation • Aggregation using Conditional Random Field

  11. Saliency Aggregation • Aggregation using Conditional Random Field

  12. Saliency Aggregation • Image-Dependent Saliency Aggregation • Upgrade the aggregation model from P Y |X θ into P Y |X θ I for each image I. • Find k nearest neighbors in the training set and then trains a saliency aggregation model using these k images. • Use the GIST descriptor to find similar images.

  13. Saliency Aggregation

  14. Experiments • Dataset • FT image saliency dataset • Stereo Saliency dataset (SS)

  15. Experiments

  16. Experiments • Robustness of Saliency Aggregation

  17. Experiments • Discussions • When all the individual methods fail to identify a salient region in an image, saliency aggregation will usually fail too. • The performance will sometimes be affected if the GIST method does not find similar images. • The aggregation requires results from all the individual methods, it is slower than each individual one.

  18. Conclusion • We presented data-driven approaches to saliency aggregation that integrate saliency analysis results from multiple individual saliency analysis methods. • Image-dependent CRF-based approach that considers the interaction among pixels, the performance gaps among individual saliency analysis methods, and the dependent of saliency analysis on individual image

More Related