Adapting Vehicle Detector to Target Domain by Adversarial Prediction Alignment

07/06/2021
by   Yohei Koga, et al.
0

While recent advancement of domain adaptation techniques is significant, most of methods only align a feature extractor and do not adapt a classifier to target domain, which would be a cause of performance degradation. We propose novel domain adaptation technique for object detection that aligns prediction output space. In addition to feature alignment, we aligned predictions of locations and class confidences of our vehicle detector for satellite images by adversarial training. The proposed method significantly improved AP score by over 5 satellite images.

READ FULL TEXT
research
03/25/2021

Multi-Target Domain Adaptation via Unsupervised Domain Classification for Weather Invariant Object Detection

Object detection is an essential technique for autonomous driving. The p...
research
03/22/2021

Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation

Many unsupervised domain adaptation (UDA) methods exploit domain adversa...
research
09/13/2021

Adversarially Trained Object Detector for Unsupervised Domain Adaptation

Unsupervised domain adaptation, which involves transferring knowledge fr...
research
02/03/2020

Unsupervised Domain Adaptive Object Detection using Forward-Backward Cyclic Adaptation

We present a novel approach to perform the unsupervised domain adaptatio...
research
05/13/2020

DAugNet: Unsupervised, Multi-source, Multi-target, and Life-long Domain Adaptation for Semantic Segmentation of Satellite Images

The domain adaptation of satellite images has recently gained an increas...
research
01/29/2021

Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency

Visual domain adaptation involves learning to classify images from a tar...
research
12/08/2020

Using Feature Alignment can Improve Clean Average Precision and Adversarial Robustness in Object Detection

The 2D object detection in clean images has been a well studied topic, b...

Please sign up or login with your details

Forgot password? Click here to reset