English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Attentive Explanations: Justifying Decisions and Pointing to the Evidence (Extended Abstract)

Park, D. H., Hendricks, L. A., Akata, Z., Rohrbach, A., Schiele, B., Darrell, T., et al. (2017). Attentive Explanations: Justifying Decisions and Pointing to the Evidence (Extended Abstract). Retrieved from http://arxiv.org/abs/1711.07373.

Item is

Files

show Files
hide Files
:
arXiv:1711.07373.pdf (Preprint), 2MB
Name:
arXiv:1711.07373.pdf
Description:
File downloaded from arXiv at 2018-01-31 11:09 arXiv admin note: text overlap with arXiv:1612.04757
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Park, Dong Huk1, Author
Hendricks, Lisa Anne1, Author
Akata, Zeynep2, Author              
Rohrbach, Anna2, Author              
Schiele, Bernt2, Author              
Darrell, Trevor1, Author
Rohrbach, Marcus1, Author
Affiliations:
1External Organizations, ou_persistent22              
2Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV
 Abstract: Deep models are the defacto standard in visual decision problems due to their impressive performance on a wide array of visual tasks. On the other hand, their opaqueness has led to a surge of interest in explainable systems. In this work, we emphasize the importance of model explanation in various forms such as visual pointing and textual justification. The lack of data with justification annotations is one of the bottlenecks of generating multimodal explanations. Thus, we propose two large-scale datasets with annotations that visually and textually justify a classification decision for various activities, i.e. ACT-X, and for question answering, i.e. VQA-X. We also introduce a multimodal methodology for generating visual and textual explanations simultaneously. We quantitatively show that training with the textual explanations not only yields better textual justification models, but also models that better localize the evidence that support their decision.

Details

show
hide
Language(s): eng - English
 Dates: 2017-11-172017
 Publication Status: Published online
 Pages: 4 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1711.07373
URI: http://arxiv.org/abs/1711.07373
BibTex Citekey: Park_arXiv1711.07373
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show