Tampere University of Technology

TUTCRIS Research Portal

Hierarchical deformable part models for heads and tails

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

Details

Original languageEnglish
Title of host publicationVISIGRAPP 2018 - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
PublisherSCITEPRESS
Pages45-55
Number of pages11
Volume5
ISBN (Electronic)9789897582905
DOIs
Publication statusPublished - 2018
Publication typeA4 Article in a conference publication
EventINTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS -
Duration: 1 Jan 1900 → …

Conference

ConferenceINTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS
Period1/01/00 → …

Abstract

Imbalanced long-tail distributions of visual class examples inhibit accurate visual detection, which is addressed by a novel Hierarchical Deformable Part Model (HDPM). HDPM constructs a sub-category hierarchy by alternating bootstrapping and Visual Similarity Network (VSN) based discovery of head and tail sub-categories. We experimentally evaluate HDPM and compare with other sub-category aware visual detection methods with a moderate size dataset (Pascal VOC 2007), and demonstrate its scalability to a large scale dataset (ILSVRC 2014 Detection Task). The proposed HDPM consistently achieves significant performance improvement in both experiments.

Keywords

  • Deformable part model, Imbalanced datasets, Localization, Long-tail distribution, Object detection, Sub-category discovery, Visual similarity network

Publication forum classification

Field of science, Statistics Finland