Gaze Embeddings for Zero-Shot Image Classification

Open Access
Authors
  • N. Karessli
  • Z. Akata ORCID logo
  • B. Schiele
  • A. Bulling
Publication date 2017
Book title 30th IEEE Conference on Computer Vision and Pattern Recognition
Book subtitle CVPR 2017 : 21-26 July 2016, Honolulu, Hawaii : proceedings
ISBN
  • 9781538604588
ISBN (electronic)
  • 9781538604571
Event 2017 IEEE Conference on Computer Vision and Pattern Recognition
Pages (from-to) 6412-6421
Publisher Piscataway, NJ: IEEE
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
Abstract
Zero-shot image classification using auxiliary information, such as attributes describing discriminative object properties, requires time-consuming annotation by domain experts. We instead propose a method that relies on human gaze as auxiliary information, exploiting that even non-expert users have a natural ability to judge class membership. We present a data collection paradigm that involves a discrimination task to increase the information content obtained from gaze data. Our method extracts discriminative descriptors from the data and learns a compatibility function between image and gaze using three novel gaze embeddings: Gaze Histograms (GH), Gaze Features with Grid (GFG) and Gaze Features with Sequence (GFS). We introduce two new gaze-annotated datasets for fine-grained image classification and show that human gaze data is indeed class discriminative, provides a competitive alternative to expert-annotated attributes, and outperforms other baselines for zero-shot image classification.
Document type Conference contribution
Language English
Published at https://doi.org/10.1109/CVPR.2017.679
Published at https://arxiv.org/abs/1611.09309
Downloads
1611.09309.pd (Accepted author manuscript)
Permalink to this page
Back