TY - GEN
T1 - Unsupervised domain adaptation of deep object detectors
AU - Majumdar, Debjeet
AU - Namboodiri, Vinay P.
PY - 2018/1/1
Y1 - 2018/1/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85069535115&partnerID=8YFLogxK
M3 - Chapter in a published conference proceeding
AN - SCOPUS:85069535115
T3 - ESANN 2018 - Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
SP - 301
EP - 306
BT - ESANN 2018 - Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
PB - i6doc.com publication
T2 - 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2018
Y2 - 25 April 2018 through 27 April 2018
ER -