TransNet: Linkage recognition with contextual nexus for hard object

Weitong Zhang, Yanling Tian, Qieshi Zhang, Jun Cheng, Huiquan Zheng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

One of the major challenges in object recognition is to propose a structure with highly performance of overlapping, small and misclassification objects, called hard object recognition. There is a contextual nexus among the spatial location and geometric characteristics of objects, which we find is essential to the recognition efficacy. We propose regress connection, nexus calculation module and linkage loss, which are contained in an improving design TransNet framework. It can not only demonstrates the interactivity of explicit nexus between objects, but also achieve better results through the integration of two mainstream methods. Adjusting the training attention through linkage loss function, thus significantly enhance the performance of hard objects. The experiment results show that our method achieves remarkable performance on PASCAL VOC2012 and MS COCO data set. Also, the head network is capable of integrating with region-based methods and gains better performance.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages75-79
Number of pages5
ISBN (Electronic)9781728137261
DOIs
Publication statusPublished - 2019 Aug
Externally publishedYes
Event2019 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2019 - Irkutsk, Russian Federation
Duration: 2019 Aug 42019 Aug 9

Publication series

Name2019 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2019

Conference

Conference2019 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2019
CountryRussian Federation
CityIrkutsk
Period19/8/419/8/9

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Optimization

Fingerprint Dive into the research topics of 'TransNet: Linkage recognition with contextual nexus for hard object'. Together they form a unique fingerprint.

Cite this