English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  DeepGaze II: A big step towards explaining all information in image-based saliency

Kümmerer, M., & Bethge, M. (2016). DeepGaze II: A big step towards explaining all information in image-based saliency. Poster presented at 16th Annual Meeting of the Vision Sciences Society (VSS 2016), St. Pete Beach, FL, USA.

Item is

Files

show Files

Locators

show
hide
Locator:
Link (Any fulltext)
Description:
-

Creators

show
hide
 Creators:
Kümmerer, M1, Author              
Bethge, M1, Author              
Affiliations:
1Werner-Reichardt-Centre for Integrative Neuroscience, University Tübingen, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: When free-viewing scenes, the first few fixations of human observers are driven in part by bottom-up attention. Over the last decade various models have been proposed to explain these fixations. We recently standardized model comparison using an information-theoretic framework and were able to show that these models captured not more than 1/3 of the explainable mutual information between image content and the fixation locations, which might be partially due to the limited data available (Kuemmerer et al, PNAS, in press). Subsequently, we have shown that this limitation can be tackled effectively by using a transfer learning strategy. Our model "DeepGaze I" uses a neural network (AlexNet) that was originally trained for object detection on the ImageNet dataset. It achieved a large improvement over the previous state of the art, explaining 56 of the explainable information (Kuemmerer et al, ICLR 2015). A new generation of object recognition models have since been developed, substantially outperforming AlexNet. The success of "DeepGaze I" and similar models suggests that features that yield good object detection performance can be exploited for better saliency prediction, and that object detection and fixation prediction performances are correlated. Here we test this hypothesis. Our new model "DeepGaze II" uses the VGG network to convert an image into a high dimensional representation, which is then fed through a second, smaller network to yield a density prediction. The second network is pre-trained using maximum-likelihood on the SALICON dataset and fine-tuned on the MIT1003 dataset. Remarkably, DeepGaze II explains 88 of the explainable information on held out data, and has since achieved top performance on the MIT Saliency Benchmark. The problem of predicting where people look under free-viewing conditions could be solved very soon. That fixation prediction performance is closely tied to object detection informs theories of attentional selection in scene viewing.

Details

show
hide
Language(s):
 Dates: 2016-08
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1167/16.12.330
BibTex Citekey: KummererB2016
 Degree: -

Event

show
hide
Title: 16th Annual Meeting of the Vision Sciences Society (VSS 2016)
Place of Event: St. Pete Beach, FL, USA
Start-/End Date: 2016-05-13 - 2016-05-18

Legal Case

show

Project information

show

Source 1

show
hide
Title: Journal of Vision
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Charlottesville, VA : Scholar One, Inc.
Pages: - Volume / Issue: 16 (12) Sequence Number: - Start / End Page: 330 Identifier: ISSN: 1534-7362
CoNE: https://pure.mpg.de/cone/journals/resource/111061245811050