Hierarchical Object Detection and Classification Using SSD Multi-Loss

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


When merging existing similar datasets, it would be attractive to benefit from a higher detection rate of objects and the additional partial ground-truth samples for improving object classification. To this end, a novel CNN detector with a hierarchical binary classification system is proposed. The detector is based on the Single-Shot multibox Detector (SSD) and inspired by the hierarchical classification used in the YOLO9000 detector. Localization and classification are separated during training, by introducing a novel loss term that handles hierarchical classification in the loss function (SSD-ML). We experiment with the proposed SSD-ML detector on the generic PASCAL VOC dataset and show that additional super-categories can be learned with minimal impact on the overall accuracy. Furthermore, we find that not all objects are required to have classification label information as classification performance only drops from 73.3 % to 70.6 % while 60 % of the label information is removed. The flexibility of the detector with respect to the different levels of details in label definitions is investigated for a traffic surveillance application, involving public and proprietary datasets with non-overlapping class definitions. Including classification label information from our dataset raises the performance significantly from 70.7 % to 82.2 %. The experiments show that the desired hierarchical labels can be learned from the public datasets, while only using box information from our dataset. In general, this shows that it is possible to combine existing datasets with similar object classes and partial annotations and benefit in terms of growth of detection rate and improved class categorization performance.

Original languageEnglish
Title of host publicationComputer Vision, Imaging and Computer Graphics Theory and Applications - 15th International Joint Conference, VISIGRAPP 2020, Revised Selected Papers
Subtitle of host publication15th International Joint Conference, VISIGRAPP 2020 Valletta, Malta, February 27–29, 2020, Revised Selected Papers
EditorsKadi Bouatouch, A. Augusto de Sousa, Manuela Chessa, Alexis Paljic, Andreas Kerren, Christophe Hurter, Giovanni Maria Farinella, Petia Radeva, Jose Braz
Place of PublicationCham
Number of pages29
ISBN (Electronic)978-3-030-94893-1
ISBN (Print)978-3-030-94892-4
Publication statusPublished - 1 Jan 2022
Event15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2020 - Valletta, Malta
Duration: 27 Feb 202029 Feb 2020

Publication series

NameCommunications in Computer and Information Science (CCIS)
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937


Conference15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2020


  • Hierarchical classification
  • SSD detector
  • Traffic surveillance


Dive into the research topics of 'Hierarchical Object Detection and Classification Using SSD Multi-Loss'. Together they form a unique fingerprint.

Cite this