Unsupervised Domain Adaptive Object Detection using Forward-Backward Cyclic Adaptation

02/03/2020
by   Siqi Yang, et al.
5

We present a novel approach to perform the unsupervised domain adaptation for object detection through forward-backward cyclic (FBC) training. Recent adversarial training based domain adaptation methods have shown their effectiveness on minimizing domain discrepancy via marginal feature distributions alignment. However, aligning the marginal feature distributions does not guarantee the alignment of class conditional distributions. This limitation is more evident when adapting object detectors as the domain discrepancy is larger compared to the image classification task, e.g. various number of objects exist in one image and the majority of content in an image is the background. This motivates us to learn domain invariance for category level semantics via gradient alignment. Intuitively, if the gradients of two domains point in similar directions, then the learning of one domain can improve that of another domain. To achieve gradient alignment, we propose Forward-Backward Cyclic Adaptation, which iteratively computes adaptation from source to target via backward hopping and from target to source via forward passing. In addition, we align low-level features for adapting holistic color/texture via adversarial training. However, the detector performs well on both domains is not ideal for target domain. As such, in each cycle, domain diversity is enforced by maximum entropy regularization on the source domain to penalize confident source-specific learning and minimum entropy regularization on target domain to intrigue target-specific learning. Theoretical analysis of the training process is provided, and extensive experiments on challenging cross-domain object detection datasets have shown the superiority of our approach over the state-of-the-art.

READ FULL TEXT

page 2

page 4

page 5

page 6

page 8

page 10

page 14

page 15

research
09/13/2021

Adversarially Trained Object Detector for Unsupervised Domain Adaptation

Unsupervised domain adaptation, which involves transferring knowledge fr...
research
12/12/2018

Strong-Weak Distribution Alignment for Adaptive Object Detection

We propose an approach for unsupervised adaptation of object detectors f...
research
09/18/2019

Wasserstein Distance Based Domain Adaptation for Object Detection

In this paper, we present an adversarial unsupervised domain adaptation ...
research
06/10/2021

AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection

Unsupervised domain adaptation for object detection is a challenging pro...
research
07/06/2021

Adapting Vehicle Detector to Target Domain by Adversarial Prediction Alignment

While recent advancement of domain adaptation techniques is significant,...
research
05/21/2016

Deep Transfer Learning with Joint Adaptation Networks

Deep networks have been successfully applied to learn transferable featu...
research
10/04/2021

Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection

In order to robustly deploy object detectors across a wide range of scen...

Please sign up or login with your details

Forgot password? Click here to reset