Domain Adaptation For Object Detection

This paper considers distribution matching in various feature level for unsupervised domain adaptation for object detection with a single stage detector.

Domain adaptation for object detection. Domain adaptive faster r cnn for object detection in the wild 1. Domain adaptive faster r cnn for object detection in the wild yuhua chen1 wen li1 christos sakaridis1 dengxin dai1 luc van gool1 2 1computer vision lab eth zurich 2visics esat psi ku leuven yuhua chen liwen csakarid dai vangool vision ee ethz ch abstract object detection typically assumes that training and test. An unsupervised approach raghuraman gopalan ruonan li and rama chellappa center for automation research university of maryland college park md 20742 usa raghuram liruonan rama umiacs umd edu abstract adapting the classifier trained on a source domain to.

Progressive domain adaptation for object detection han kai hsu1 wei chih hung1 hung yu tseng1 chun han yao2 yi hsuan tsai3 maneesh singh4 ming hsuan yang1 5 1university of california merced 2university of california san diego 3nec laboratories america 4verisk analytics 5google abstract recent deep learning methods for object detection rely on a large amount of bounding box annotations. This paper presents a novel uda model which integrates both image and feature level based adaptations to solve the cross domain object detection problem. Domain adaptive object detection fatemeh mirrashed 1 vlad i.

The first step makes the detector robust to low level differences and the second step adapts the classifiers to changes in the high level features. Morariu behjat siddiquie2 rogerio s. We propose a domain adaptation approach for object detection.

Implementation of our paper progressive domain adaptation for object detection based on pytorch faster rcnn and pytorch cyclegan. Domain adaptation provides a solution by adapting existing labels to the target testing data. Collecting these annotations is laborious and costly yet supervised models do not generalize well when testing on images from a different distribution.

For the first step we use a style transfer method for pixel adaptation of source images to the target domain. We find that enforcing low distance in the. The object detection task assumes that training and test data are drawn from the same distribution.

Domain adaptation for object recognition. Progressive domain adaptation for object detection. However in a real environment there is a domain gap between training and test data which leads to degrading performance significantly.