ServiceNow Research

LOOC: Localize Overlapping Objects with Count Supervision

Abstract

Acquiring count annotations generally requires less human effort than point-level and bounding box annotations. Thus, we propose the novel problem setup of localizing objects in dense scenes under this weaker supervision. We propose LOOC, a method to Localize Overlapping Objects with Count supervision. We train LOOC by alternating between two stages. In the first stage, LOOC learns to generate pseudo point-level annotations in a semi-supervised manner. In the second stage, LOOC uses a fully-supervised localization method that trains on these pseudo labels. The localization method is used to progressively improve the quality of the pseudo labels. We conducted experiments on popular counting datasets. For localization, LOOC achieves a strong new baseline in the novel problem setup where only count supervision is available. For counting, LOOC outperforms current state-of-the-art methods that only use count as their supervision. Code is available at: this https URL.

Publication
International Conference on Image Processing (ICIP)
Issam H. Laradji
Issam H. Laradji
Research Scientist

Research Scientist at Low Data Learning located at Vancouver, BC, Canada.

Rafael Pardinas
Rafael Pardinas
Applied Research Scientist

Applied Research Scientist at Human Decision Support located at London, UK.

David Vazquez
David Vazquez
Manager of Research Programs

Manager of Research Programs at Research Management located at Montreal, QC, Canada.