![]() ![]() In comparison to recent methods, we achieve state-of-the-art performance using a much simpler procedure for the training. The benefit of the approaches is demonstrated by evaluating different domain shift scenarios on public data sets. Hence, DA is accomplished without architectural add-ons and additional hyper-parameters. ![]() We propose to align either color histograms or mean and covariance of the source images towards the target domain. In contrast, we look at the problem from a new perspective and keep it simple by solely matching image statistics between source and target domain. Recent state-of-the-art methods try to reduce the domain gap using an adversarial training strategy which increases the performance but at the same time the complexity of the training procedure. In this work, we focus on unsupervised DA: maintaining the detection accuracy across different data distributions, when only unlabeled images are available of the target domain. Tackling the shift is known as Domain Adaptation (DA). In order to overcome this problem, it is necessary to consider a shift between source and target domains. Additionally, we show that applying our techniques significantly reduces the amount of synthetic data needed to learn a general model and thus increases the value of simulation.Īpplying an object detector, which is neither trained nor fine-tuned on data close to the final application, often leads to a substantial performance drop. Applying an object detector, which is neither trained nor fine-tuned on data close to the final application, often leads to a substantial performance drop. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |