scholarly journals GANana: Unsupervised Domain Adaptation for Volumetric Regression of Fruit

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Zane K. J. Hartley ◽  
Aaron S. Jackson ◽  
Michael Pound ◽  
Andrew P. French
Keyword(s):  
3D Reconstruction ◽  
Domain Adaptation ◽  
Synthetic Data ◽  
3D Models ◽  
Training Data ◽  
Plant Phenotyping ◽  
Size Estimation ◽  
Unsupervised Domain Adaptation ◽  
High Quality Image ◽  
Modelling Environment

3D reconstruction of fruit is important as a key component of fruit grading and an important part of many size estimation pipelines. Like many computer vision challenges, the 3D reconstruction task suffers from a lack of readily available training data in most domains, with methods typically depending on large datasets of high-quality image-model pairs. In this paper, we propose an unsupervised domain-adaptation approach to 3D reconstruction where labelled images only exist in our source synthetic domain, and training is supplemented with different unlabelled datasets from the target real domain. We approach the problem of 3D reconstruction using volumetric regression and produce a training set of 25,000 pairs of images and volumes using hand-crafted 3D models of bananas rendered in a 3D modelling environment (Blender). Each image is then enhanced by a GAN to more closely match the domain of photographs of real images by introducing a volumetric consistency loss, improving performance of 3D reconstruction on real images. Our solution harnesses the cost benefits of synthetic data while still maintaining good performance on real world images. We focus this work on the task of 3D banana reconstruction from a single image, representing a common task in plant phenotyping, but this approach is general and may be adapted to any 3D reconstruction task including other plant species and organs.

scholarly journals Phenomenal: An automatic open source library for 3D shoot architecture reconstruction and analysis for image-based plant phenotyping

2019 ◽  
Author(s):  
Simon Artzet ◽  
Tsu-Wei Chen ◽  
Jérôme Chopard ◽  
Nicolas Brichet ◽  
Michael Mielewczik ◽  
...  
Keyword(s):  
Open Source ◽  
High Throughput ◽  
Synthetic Data ◽  
3D Models ◽  
Plant Phenotyping ◽  
Published Data ◽  
Data Sets ◽  
Quantitative Measurements ◽  
Workflow System ◽  
Architectural Features

AbstractIn the era of high-throughput visual plant phenotyping, it is crucial to design fully automated and flexible workflows able to derive quantitative traits from plant images. Over the last years, several software supports the extraction of architectural features of shoot systems. Yet currently no end-to-end systems are able to extract both 3D shoot topology and geometry of plants automatically from images on large datasets and a large range of species. In particular, these software essentially deal with dicotyledons, whose architecture is comparatively easier to analyze than monocotyledons. To tackle these challenges, we designed the Phenomenal software featured with: (i) a completely automatic workflow system including data import, reconstruction of 3D plant architecture for a range of species and quantitative measurements on the reconstructed plants; (ii) an open source library for the development and comparison of new algorithms to perform 3D shoot reconstruction and (iii) an integration framework to couple workflow outputs with existing models towards model-assisted phenotyping. Phenomenal analyzes a large variety of data sets and species from images of high-throughput phenotyping platform experiments to published data obtained in different conditions and provided in a different format. Phenomenal has been validated both on manual measurements and synthetic data simulated by 3D models. It has been also tested on other published datasets to reproduce a published semi-automatic reconstruction workflow in an automatic way. Phenomenal is available as an open-source software on a public repository.

scholarly journals Harmonized Segmentation of Neonatal Brain MRI

2021 ◽  
Vol 15 ◽  
Author(s):  
Irina Grigorescu ◽  
Lucy Vanes ◽  
Alena Uus ◽  
Dafnis Batalle ◽  
Lucilio Cordero-Grande ◽  
...  
Keyword(s):  
Cortical Thickness ◽  
Domain Adaptation ◽  
Brain Mri ◽  
Medical Image Segmentation ◽  
Training Data ◽  
Imaging Data ◽  
Target Domain ◽  
Tissue Segmentation ◽  
Unsupervised Domain Adaptation ◽  
Preterm Born

Deep learning based medical image segmentation has shown great potential in becoming a key part of the clinical analysis pipeline. However, many of these models rely on the assumption that the train and test data come from the same distribution. This means that such methods cannot guarantee high quality predictions when the source and target domains are dissimilar due to different acquisition protocols, or biases in patient cohorts. Recently, unsupervised domain adaptation techniques have shown great potential in alleviating this problem by minimizing the shift between the source and target distributions, without requiring the use of labeled data in the target domain. In this work, we aim to predict tissue segmentation maps on T2-weighted magnetic resonance imaging data of an unseen preterm-born neonatal population, which has both different acquisition parameters and population bias when compared to our training data. We achieve this by investigating two unsupervised domain adaptation techniques with the objective of finding the best solution for our problem. We compare the two methods with a baseline fully-supervised segmentation network and report our results in terms of Dice scores obtained on our source test dataset. Moreover, we analyse tissue volumes and cortical thickness measures of the harmonized data on a subset of the population matched for gestational age at birth and postmenstrual age at scan. Finally, we demonstrate the applicability of the harmonized cortical gray matter maps with an analysis comparing term and preterm-born neonates and a proof-of-principle investigation of the association between cortical thickness and a language outcome measure.

scholarly journals Weighted elastic net for unsupervised domain adaptation with application to age prediction from DNA methylation data

2019 ◽  
Vol 35 (14) ◽  
pp. i154-i163 ◽  
Author(s):  
Lisa Handl ◽  
Adrin Jalali ◽  
Michael Scherer ◽  
Ralf Eggeling ◽  
Nico Pfeifer
Keyword(s):  
Dna Methylation ◽  
Computational Biology ◽  
Domain Adaptation ◽  
Real Data ◽  
Elastic Net ◽  
Training Data ◽  
Supplementary Information ◽  
Methylation Data ◽  
Unsupervised Domain Adaptation ◽  
Age Prediction

Abstract Motivation Predictive models are a powerful tool for solving complex problems in computational biology. They are typically designed to predict or classify data coming from the same unknown distribution as the training data. In many real-world settings, however, uncontrolled biological or technical factors can lead to a distribution mismatch between datasets acquired at different times, causing model performance to deteriorate on new data. A common additional obstacle in computational biology is scarce data with many more features than samples. To address these problems, we propose a method for unsupervised domain adaptation that is based on a weighted elastic net. The key idea of our approach is to compare dependencies between inputs in training and test data and to increase the cost of differently behaving features in the elastic net regularization term. In doing so, we encourage the model to assign a higher importance to features that are robust and behave similarly across domains. Results We evaluate our method both on simulated data with varying degrees of distribution mismatch and on real data, considering the problem of age prediction based on DNA methylation data across multiple tissues. Compared with a non-adaptive standard model, our approach substantially reduces errors on samples with a mismatched distribution. On real data, we achieve far lower errors on cerebellum samples, a tissue which is not part of the training data and poorly predicted by standard models. Our results demonstrate that unsupervised domain adaptation is possible for applications in computational biology, even with many more features than samples. Availability and implementation Source code is available at https://github.com/PfeiferLabTue/wenda. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation

2020 ◽  
Vol 29 (01) ◽  
pp. 129-138 ◽  
Author(s):  
Anirudh Choudhary ◽  
Li Tong ◽  
Yuanda Zhu ◽  
May D. Wang
Keyword(s):  
Deep Learning ◽  
Medical Imaging ◽  
Large Scale ◽  
Domain Adaptation ◽  
Rapid Development ◽  
Synthetic Data ◽  
Feature Space ◽  
Imaging Informatics ◽  
Training Data ◽  
Domain Transformation

Introduction: There has been a rapid development of deep learning (DL) models for medical imaging. However, DL requires a large labeled dataset for training the models. Getting large-scale labeled data remains a challenge, and multi-center datasets suffer from heterogeneity due to patient diversity and varying imaging protocols. Domain adaptation (DA) has been developed to transfer the knowledge from a labeled data domain to a related but unlabeled domain in either image space or feature space. DA is a type of transfer learning (TL) that can improve the performance of models when applied to multiple different datasets. Objective: In this survey, we review the state-of-the-art DL-based DA methods for medical imaging. We aim to summarize recent advances, highlighting the motivation, challenges, and opportunities, and to discuss promising directions for future work in DA for medical imaging. Methods: We surveyed peer-reviewed publications from leading biomedical journals and conferences between 2017-2020, that reported the use of DA in medical imaging applications, grouping them by methodology, image modality, and learning scenarios. Results: We mainly focused on pathology and radiology as application areas. Among various DA approaches, we discussed domain transformation (DT) and latent feature-space transformation (LFST). We highlighted the role of unsupervised DA in image segmentation and described opportunities for future development. Conclusion: DA has emerged as a promising solution to deal with the lack of annotated training data. Using adversarial techniques, unsupervised DA has achieved good performance, especially for segmentation tasks. Opportunities include domain transferability, multi-modal DA, and applications that benefit from synthetic data.

scholarly journals Unpaired Multi-Domain Image Generation via Regularized Conditional GANs

2018 ◽  
Author(s):  
Xudong Mao ◽  
Qing Li
Keyword(s):  
Computer Vision ◽  
Domain Adaptation ◽  
Generative Models ◽  
Training Data ◽  
Image Generation ◽  
Not Given ◽  
Unsupervised Domain Adaptation ◽  
Paired Samples ◽  
Proposed Model ◽  
Great Progress

In this paper, we study the problem of multi-domain image generation, the goal of which is to generate pairs of corresponding images from different domains. With the recent development in generative models, image generation has achieved great progress and has been applied to various computer vision tasks. However, multi-domain image generation may not achieve the desired performance due to the difficulty of learning the correspondence of different domain images, especially when the information of paired samples is not given. To tackle this problem, we propose Regularized Conditional GAN (RegCGAN) which is capable of learning to generate corresponding images in the absence of paired training data. RegCGAN is based on the conditional GAN, and we introduce two regularizers to guide the model to learn the corresponding semantics of different domains. We evaluate the proposed model on several tasks for which paired training data is not given, including the generation of edges and photos, the generation of faces with different attributes, etc. The experimental results show that our model can successfully generate corresponding images for all these tasks, while outperforms the baseline methods. We also introduce an approach of applying RegCGAN to unsupervised domain adaptation.

scholarly journals Adversarial Learning for Effective Detector Training via Synthetic Data

2020 ◽  
pp. short16-1-short16-9
Author(s):  
Vadim Gorbachev ◽  
Andrey Nikitin ◽  
Ilya Basharov
Keyword(s):  
Real Life ◽  
Synthetic Data ◽  
Real Data ◽  
3D Models ◽  
Training Data ◽  
Real World Data ◽  
Aerial Vehicle ◽  
Effective Use ◽  
Detection And Localization ◽  
Direct Use

Current neural network-based algorithms for object detection require a huge amount of training data. Creation and annotation of specific datasets for real-life applications require significant human and time resources that are not always available. This issue substantially prevents the successful deployment of AI algorithms in industrial tasks. One possible solutions is a synthesis of train images by rendering 3D models of target objects, which allows effortless automatic annotation. However, direct use of synthetic training datasets does not usually result in an increase of the algorithms’ quality on test data due to differences in data domains. In this paper, we propose the adversarial architecture and training method for a CNN-based detector, which allows the effective use of synthesized images in case of a lack of labeled real-world data. The method was successfully tested on real data and applied for the development of unmanned aerial vehicle (UAV) detection and localization system.

scholarly journals Pheno4D: A spatio-temporal dataset of maize and tomato plant point clouds for phenotyping and advanced plant analysis

PLoS ONE ◽  
2021 ◽  
Vol 16 (8) ◽  
pp. e0256340
Author(s):  
David Schunck ◽  
Federico Magistri ◽  
Radu Alexandru Rosu ◽  
André Cornelißen ◽  
Nived Chebrolu ◽  
...  
Keyword(s):  
High Resolution ◽  
3D Reconstruction ◽  
Point Clouds ◽  
Training Data ◽  
Plant Phenotyping ◽  
Growth Stages ◽  
Plant Analysis ◽  
Rigid Registration ◽  
3D Point Clouds ◽  
Spatio Temporal

Understanding the growth and development of individual plants is of central importance in modern agriculture, crop breeding, and crop science. To this end, using 3D data for plant analysis has gained attention over the last years. High-resolution point clouds offer the potential to derive a variety of plant traits, such as plant height, biomass, as well as the number and size of relevant plant organs. Periodically scanning the plants even allows for performing spatio-temporal growth analysis. However, highly accurate 3D point clouds from plants recorded at different growth stages are rare, and acquiring this kind of data is costly. Besides, advanced plant analysis methods from machine learning require annotated training data and thus generate intense manual labor before being able to perform an analysis. To address these issues, we present with this dataset paper a multi-temporal dataset featuring high-resolution registered point clouds of maize and tomato plants, which we manually labeled for computer vision tasks, such as for instance segmentation and 3D reconstruction, providing approximately 260 million labeled 3D points. To highlight the usability of the data and to provide baselines for other researchers, we show a variety of applications ranging from point cloud segmentation to non-rigid registration and surface reconstruction. We believe that our dataset will help to develop new algorithms to advance the research for plant phenotyping, 3D reconstruction, non-rigid registration, and deep learning on raw point clouds. The dataset is freely accessible at https://www.ipb.uni-bonn.de/data/pheno4d/.

scholarly journals Unsupervised Domain Adaptation with Dual-Scheme Fusion Network for Medical Image Segmentation

2020 ◽  
Author(s):  
Danbing Zou ◽  
Qikui Zhu ◽  
Pingkun Yan
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
Network Performance ◽  
Domain Adaptation ◽  
Medical Image Segmentation ◽  
Training Data ◽  
Tumor Segmentation ◽  
Target Domain ◽  
Brain Tumor Segmentation ◽  
Unsupervised Domain Adaptation

Domain adaptation aims to alleviate the problem of retraining a pre-trained model when applying it to a different domain, which requires large amount of additional training data of the target domain. Such an objective is usually achieved by establishing connections between the source domain labels and target domain data. However, this imbalanced source-to-target one way pass may not eliminate the domain gap, which limits the performance of the pre-trained model. In this paper, we propose an innovative Dual-Scheme Fusion Network (DSFN) for unsupervised domain adaptation. By building both source-to-target and target-to-source connections, this balanced joint information flow helps reduce the domain gap to further improve the network performance. The mechanism is further applied to the inference stage, where both the original input target image and the generated source images are segmented with the proposed joint network. The results are fused to obtain more robust segmentation. Extensive experiments of unsupervised cross-modality medical image segmentation are conducted on two tasks -- brain tumor segmentation and cardiac structures segmentation. The experimental results show that our method achieved significant performance improvement over other state-of-the-art domain adaptation methods.

scholarly journals UNSUPERVISED DOMAIN ADAPTATION USING A TEACHER-STUDENT NETWORK FOR CROSS-CITY CLASSIFICATION OF SENTINEL-2 IMAGES

2020 ◽  
Vol XLIII-B2-2020 ◽  
pp. 1569-1574
Author(s):  
J. Hu ◽  
L. Mou ◽  
X. X. Zhu
Keyword(s):  
Remote Sensing ◽  
Domain Adaptation ◽  
Training Data ◽  
Target Domain ◽  
Source Domain ◽  
Unsupervised Domain Adaptation ◽  
Teacher Student ◽  
The Mean ◽  
The City ◽  
Teacher Model

Abstract. A machine learning algorithm in remote sensing often fails in the inference of a data set which has a different geographic location than the training data. This is because data of different locations have different underlying distributions caused by complicated reasons, such as the climate and the culture. For a large scale or a global scale task, this issue becomes relevant since it is extremely expensive to collect training data over all regions of interest. Unsupervised domain adaptation is a potential solution for this issue. Its goal is to train an algorithm in a source domain and generalize it to a target domain without using any label from the target domain. Those domains can be associated to geographic locations in remote sensing. In this paper, we attempt to adapt the unsupervised domain adaptation strategy by using a teacher-student network, mean teacher model, to investigate a cross-city classification problem in remote sensing. The mean teacher model consists of two identical networks, a teacher network and a student network. The objective function is a combination of a classification loss and a consistent loss. The classification loss works within the source domain (a city) and aims at accomplishing the goal of classification. The consistent loss works within the target domain (another city) and aims at transferring the knowledge learned from the source to the target. In this paper, two cross-city scenarios are set up. First, we train the model with the data of the city Munich, Germany, and test it on the data of the city Moscow, Russia. The second one is carried out by switching the training and testing data. For comparison, the baseline algorithm is a ResNet-18 which is also chosen as the backbone for the teacher and student networks in the mean teacher model. With 10 independent runs, in the first scenario, the mean teacher model has a mean overall accuracy of 53.38% which is slightly higher than the mean overall accuracy of the baseline, 52.21%. However, in the second scenario, the mean teacher model has a mean overall accuracy of 62.71% which is 5% higher than the mean overall accuracy of the baseline, 57.76%. This work demonstrates that it is worthy to explore the potential of the mean teacher model to solve the domain adaptation issues in remote sensing.

Sign in / Sign up

Export Citation Format

Share Document