Unsupervised domain adaptation of deep object detectors

Debjeet Majumdar, Vinay P. Namboodiri

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

Abstract

Domain adaptation has been understood and adopted in vision. Recently with the advent of deep learning there are a number of techniques that propose methods for deep learning based domain adaptation. However, the methods proposed have been used for adapting object classification techniques. In this paper, we solve for domain adaptation of object detection that is more commonly used. We adapt deep adaptation techniques for the Faster R-CNN framework. The techniques that we adapt are the recent techniques based on Gradient Reversal and Maximum Mean Discrepancy (MMD) reduction based techniques. Among them we show that the MK-MMD based method when used appropriately provides the best results. We analyze our model with standard real world settings by using Pascal VOC as source and MS-COCO as target and show a gain of 2.5 mAP at IoU of 0.5 over a source only trained model. We show that this improvement is statistically significant.

Original languageEnglish
Title of host publicationESANN 2018 - Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Publisheri6doc.com publication
Pages301-306
Number of pages6
ISBN (Electronic)9782875870476
Publication statusPublished - 1 Jan 2018
Event26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2018 - Bruges, Belgium
Duration: 25 Apr 201827 Apr 2018

Publication series

NameESANN 2018 - Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Conference

Conference26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2018
CountryBelgium
CityBruges
Period25/04/1827/04/18

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems

Fingerprint Dive into the research topics of 'Unsupervised domain adaptation of deep object detectors'. Together they form a unique fingerprint.

Cite this