Eye-tracking Data for Weakly Supervised Object Detection

Ching Hsi Tseng, Yen Hsu, Shyan Ming Yuan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We propose a weakly supervised object detection network based on eye-tracking data. A large number of training samples cannot be used due to the following problems: (1) the labels of training samples in object detection are not all pixel-level and (2) the cost of labeling is too high. Thus, we introduce a framework whose input combines images with only image-level labels and eye-tracking data. Based on the position given by the eye-tracking data, the framework has effective performance even in the case of incomplete sample annotation. Thus, we use an eye-tracker to collect the data on the most interesting area in the sample images and present the data in the fixations way. Then, the bounding boxes produced by the fixations data and the original image-level label become the input data of the object detection network. In this way, eye-tracking data helps us selecting the bounding boxes and providing detailed location information. Experiment results verify that the framework is effective with the support of eye-tracking data.

Original languageEnglish
Title of host publication2nd IEEE Eurasia Conference on IOT, Communication and Engineering 2020, ECICE 2020
EditorsTeen-Hang Meen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages223-225
Number of pages3
ISBN (Electronic)9781728180601
DOIs
StatePublished - 23 Oct 2020
Event2nd IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2020 - Yunlin, Taiwan
Duration: 23 Oct 202025 Oct 2020

Publication series

Name2nd IEEE Eurasia Conference on IOT, Communication and Engineering 2020, ECICE 2020

Conference

Conference2nd IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2020
CountryTaiwan
CityYunlin
Period23/10/2025/10/20

Keywords

  • CNN
  • eye-tracking
  • YOLOv3

Fingerprint Dive into the research topics of 'Eye-tracking Data for Weakly Supervised Object Detection'. Together they form a unique fingerprint.

Cite this