Gaze Embeddings for Zero-Shot Image Classification

Nour Karessli, Zeynep Akata, Bernt Schiele, Andreas Bulling; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4525-4534

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.

Related Material


[pdf] [arXiv] [poster] [video]
[bibtex]
@InProceedings{Karessli_2017_CVPR,
author = {Karessli, Nour and Akata, Zeynep and Schiele, Bernt and Bulling, Andreas},
title = {Gaze Embeddings for Zero-Shot Image Classification},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}