Style transfer based domain adaptation for vegetationsegmentation with optical imagery

2021 ◽  
Author(s):  
Fabian Schenkel ◽  
Stefan Hinz ◽  
Wolfgang Middelmann
Keyword(s):  
Domain Adaptation ◽  
Style Transfer ◽  
Optical Imagery

scholarly journals Learning Domain Invariant Representation via Self-Rugularization

2021 ◽  
Vol 24 (4) ◽  
pp. 382-391
Author(s):  
Jaeguk Hyun ◽  
ChanYong Lee ◽  
Hoseong Kim ◽  
Hyunjung Yoo ◽  
Eunjin Koh
Keyword(s):  
Domain Adaptation ◽  
Regularization Methods ◽  
Invariant Representation ◽  
Large Dataset ◽  
Style Transfer ◽  
Unsupervised Domain Adaptation ◽  
Loss Term ◽  
Target Data ◽  
Small Dataset ◽  
Feature Alignment

Unsupervised domain adaptation often gives impressive solutions to handle domain shift of data. Most of current approaches assume that unlabeled target data to train is abundant. This assumption is not always true in practices. To tackle this issue, we propose a general solution to solve the domain gap minimization problem without any target data. Our method consists of two regularization steps. The first step is a pixel regularization by arbitrary style transfer. Recently, some methods bring style transfer algorithms to domain adaptation and domain generalization process. They use style transfer algorithms to remove texture bias in source domain data. We also use style transfer algorithms for removing texture bias, but our method depends on neither domain adaptation nor domain generalization paradigm. The second regularization step is a feature regularization by feature alignment. Adding a feature alignment loss term to the model loss, the model learns domain invariant representation more efficiently. We evaluate our regularization methods from several experiments both on small dataset and large dataset. From the experiments, we show that our model can learn domain invariant representation as much as unsupervised domain adaptation methods.

scholarly journals Relative Camera Pose Estimation using Synthetic Data with Domain Adaptation via Cycle-Consistent Adversarial Networks

2021 ◽  
Vol 102 (4) ◽  
Author(s):  
Chenhao Yang ◽  
Yuyi Liu ◽  
Andreas Zell
Keyword(s):  
Pose Estimation ◽  
Autonomous Navigation ◽  
Domain Adaptation ◽  
Synthetic Data ◽  
Estimation Methods ◽  
Visual Localization ◽  
Style Transfer ◽  
Camera Pose Estimation ◽  
Camera Pose ◽  
Synthetic Images

AbstractLearning-based visual localization has become prospective over the past decades. Since ground truth pose labels are difficult to obtain, recent methods try to learn pose estimation networks using pixel-perfect synthetic data. However, this also introduces the problem of domain bias. In this paper, we first build a Tuebingen Buildings dataset of RGB images collected by a drone in urban scenes and create a 3D model for each scene. A large number of synthetic images are generated based on these 3D models. We take advantage of image style transfer and cycle-consistent adversarial training to predict the relative camera poses of image pairs based on training over synthetic environment data. We propose a relative camera pose estimation approach to solve the continuous localization problem for autonomous navigation of unmanned systems. Unlike those existing learning-based camera pose estimation methods that train and test in a single scene, our approach successfully estimates the relative camera poses of multiple city locations with a single trained model. We use the Tuebingen Buildings and the Cambridge Landmarks datasets to evaluate the performance of our approach in a single scene and across-scenes. For each dataset, we compare the performance between real images and synthetic images trained models. We also test our model in the indoor dataset 7Scenes to demonstrate its generalization ability.

A New Deep Learning Method Based on Unsupervised Domain Adaptation and Re-ranking in Person Re-identification

2020 ◽  
Vol 34 (13) ◽  
pp. 2052011
Author(s):  
Chunhui Wang ◽  
Hua Han ◽  
Xiwu Shang ◽  
Xiaoli Zhao
Keyword(s):  
Deep Learning ◽  
Real World ◽  
Domain Adaptation ◽  
Learning Algorithm ◽  
Hot Spot ◽  
Feature Learning ◽  
Transfer Model ◽  
Style Transfer ◽  
Unsupervised Domain Adaptation ◽  
The Cost

Person re-identification (Re-ID) is a research hot spot in the field of intelligent video analysis, and it is also a challenging task. As the number of samples grows larger, traditional metric and feature learning methods fall into bottleneck, while it just meets the needs of deep learning algorithm, which perform very well in person re-identification. Although they have achieved good results in the field of supervised learning, their application in real-world scenarios is not very satisfactory. This is mainly because in the real world, a huge number of labeled images are hard to obtain, and even if they are obtained, the cost is expensive. Meanwhile, the performance of deep learning in unsupervised metrics is not ideal. For solving the problem, we propose a new method based on unsupervised domain adaptation (UDA) and re-ranking, and name it UDA[Formula: see text]. As for this method, we first train a camera-aware style transfer model to gain camstyle images. Then we further reduce the difference between the domain of the target and source by using invariant feature, and further improve their commonality. In addition, re-ranking is also introduced to optimize the matching results. This method can not only reduce the cost of obtaining labeled data, but also improve the accuracy. Experimental results show that our method can outperform the most advanced method by 4% on Rank-1 and 14% on mAP. The results also better confirm the effectiveness of Re-ranking module and provide a new idea for domain adaptation by unsupervised methods in the future.

Domain Adaptation via Image Style Transfer

2020 ◽  
pp. 137-156
Author(s):  
Amir Atapour-Abarghouei ◽  
Toby P. Breckon
Keyword(s):  
Domain Adaptation ◽  
Style Transfer

Domain Adaptation for Plant Organ Detection with Style Transfer

2021 ◽  
Author(s):  
Chrisbin James ◽  
Yanyang Gu ◽  
Scott Chapman ◽  
Wei Guo ◽  
Etienne David ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Style Transfer ◽  
Plant Organ

scholarly journals Demystifying Neural Style Transfer

2017 ◽  
Author(s):  
Yanghao Li ◽  
Naiyan Wang ◽  
Jiaying Liu ◽  
Xiaodi Hou
Keyword(s):  
Domain Adaptation ◽  
Second Order ◽  
Polynomial Kernel ◽  
Important Research ◽  
Feature Maps ◽  
Style Transfer ◽  
Maximum Mean Discrepancy ◽  
Research Fields ◽  
Gram Matrices ◽  
Order Polynomial

Neural Style Transfer has recently demonstrated very exciting results which catches eyes in both academia and industry. Despite the amazing results, the principle of neural style transfer, especially why the Gram matrices could represent style remains unclear. In this paper, we propose a novel interpretation of neural style transfer by treating it as a domain adaptation problem. Specifically, we theoretically show that matching the Gram matrices of feature maps is equivalent to minimize the Maximum Mean Discrepancy (MMD) with the second order polynomial kernel. Thus, we argue that the essence of neural style transfer is to match the feature distributions between the style images and the generated images. To further support our standpoint, we experiment with several other distribution alignment methods, and achieve appealing results. We believe this novel interpretation connects these two important research fields, and could enlighten future researches.

scholarly journals A Domain Adaptive Person Re-Identification Based on Dual Attention Mechanism and Camstyle Transfer

Algorithms ◽  
2021 ◽  
Vol 14 (12) ◽  
pp. 361
Author(s):  
Chengyan Zhong ◽  
Guanqiu Qi ◽  
Neal Mazur ◽  
Sarbani Banerjee ◽  
Devanshi Malaviya ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Domain Adaptation ◽  
Attention Mechanism ◽  
Training Set ◽  
Stream Network ◽  
Style Transfer ◽  
Network Feature ◽  
Image Capturing ◽  
The Difference ◽  
Target Sets

Due to the variation in the image capturing process, the difference between source and target sets causes a challenge in unsupervised domain adaptation (UDA) on person re-identification (re-ID). Given a labeled source training set and an unlabeled target training set, this paper focuses on improving the generalization ability of the re-ID model on the target testing set. The proposed method enforces two properties at the same time: (1) camera invariance is achieved through the positive learning formed by unlabeled target images and their camera style transfer counterparts; and (2) the robustness of the backbone network feature extraction is improved, and the accuracy of feature extraction is enhanced by adding a position-channel dual attention mechanism. The proposed network model uses a classic dual-stream network. Comparative experimental results on three public benchmarks prove the superiority of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document