Weakly Supervised Segmentation Pretraining for Plant Cover Prediction

Körschens, Matthias; Bodesheim, Paul; Römermann, Christine; Bucher, Solveig Franziska; Migliavacca, Mirco; Ulrich, Josephine; Denzler, Joachim

doi:10.1007/978-3-030-92659-5_38

Cited by 4 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data annotation by an expert with domainspecific knowledge is a tedious and expensive task. The DL community is exploring various strategies to break this dependency on a large quantity of annotated data to train DL models in a label-efficient manner, including approaches like active learning (Nagasubramanian et al, 2021), transfer learning (Jiang and Li, 2020), weakly supervised learning (Ghosal et al, 2019;Körschens et al, 2021) and the more recent advances in selfsupervised learning (Jing and Tian, 2020;Marin Zapata et al, 2021;Nagasubramanian et al, 2022). Transfer learning has been widely utilized in plant phenomics applications for classification and segmentation tasks (Wang et al, 2019;Kattenborn et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Self-supervised maize kernel classification and segmentation for embryo identification

et al. 2023

View full text Add to dashboard Cite

IntroductionComputer vision and deep learning (DL) techniques have succeeded in a wide range of diverse fields. Recently, these techniques have been successfully deployed in plant science applications to address food security, productivity, and environmental sustainability problems for a growing global population. However, training these DL models often necessitates the large-scale manual annotation of data which frequently becomes a tedious and time-and-resource- intensive process. Recent advances in self-supervised learning (SSL) methods have proven instrumental in overcoming these obstacles, using purely unlabeled datasets to pre-train DL models.MethodsHere, we implement the popular self-supervised contrastive learning methods of NNCLR Nearest neighbor Contrastive Learning of visual Representations) and SimCLR (Simple framework for Contrastive Learning of visual Representations) for the classification of spatial orientation and segmentation of embryos of maize kernels. Maize kernels are imaged using a commercial high-throughput imaging system. This image data is often used in multiple downstream applications across both production and breeding applications, for instance, sorting for oil content based on segmenting and quantifying the scutellum’s size and for classifying haploid and diploid kernels.Results and discussionWe show that in both classification and segmentation problems, SSL techniques outperform their purely supervised transfer learning-based counterparts and are significantly more annotation efficient. Additionally, we show that a single SSL pre-trained model can be efficiently finetuned for both classification and segmentation, indicating good transferability across multiple downstream applications. Segmentation models with SSL-pretrained backbones produce DICE similarity coefficients of 0.81, higher than the 0.78 and 0.73 of those with ImageNet-pretrained and randomly initialized backbones, respectively. We observe that finetuning classification and segmentation models on as little as 1% annotation produces competitive results. These results show SSL provides a meaningful step forward in data efficiency with agricultural deep learning and computer vision.

show abstract

Section: Introductionmentioning

confidence: 99%

Self-supervised maize kernel classification and segmentation for embryo identification

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Data annotation by an expert with domain-specific knowledge is a tedious and expensive task. The DL community is exploring various strategies to break this dependency on a large quantity of annotated data to train DL models in a label-efficient manner, including approaches like active learning [10], transfer learning [11], weakly supervised learning [12, 13] and the more recent advances in self-supervised learning [14, 15]. In this work, we focus on deploying self-supervised learning approaches to the problem of characterizing maize kernels that are imaged in a commercial high-throughput seed imaging system (Qsorter technologies [16]).…”

Section: Introductionmentioning

confidence: 99%

Self-Supervised Maize Kernel Classification and Segmentation for Embryo Identification

Dong

Nagasubramanian

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

Computer vision and deep learning (DL) techniques have succeeded in a wide range of diverse fields. Recently, these techniques have been successfully deployed in plant science applications to address food security, productivity, and environmental sustainability problems for a growing global population. However, training these DL models often necessitates the large-scale manual annotation of data which frequently becomes a tedious and time-and-resource-intensive process. Recent advances in self-supervised learning (SSL) methods have proven instrumental in overcoming these obstacles, using purely unlabeled datasets to pre-train DL models. Here, we implement the popular self-supervised contrastive learning methods of NNCLR (Nearest neighbor Contrastive Learning of visual Representations) and SimCLR (Simple framework for Contrastive Learning of visual Representations) for the classification of spatial orientation and segmentation of embryos of maize kernels. Maize kernels are imaged using a commercial high-throughput imaging system. This image data is often used in multiple downstream applications across both production and breeding applications, for instance, sorting for oil content based on segmenting and quantifying the scutellum's size and for classifying haploid and diploid kernels. We show that in both classification and segmentation problems, SSL techniques outperform their purely supervised transfer learning-based counterparts and are significantly more annotation efficient. Additionally, we show that a single SSL pre-trained model can be efficiently finetuned for both classification and segmentation, indicating good transferability across multiple downstream applications. Segmentation models with SSL-pretrained backbones produce DICE similarity coefficients of 0.81, higher than the 0.78 and 0.73 of those with ImageNet-pretrained and randomly initialized backbones, respectively. We observe that finetuning classification and segmentation models on as little as 1% annotation produces competitive results. These results show SSL provides a meaningful step forward in data efficiency with agricultural deep learning and computer vision.

show abstract

Improving Data Efficiency for Plant Cover Prediction with Label Interpolation and Monte-Carlo Cropping

Körschens,

Bucher,

Römermann

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Weakly Supervised Segmentation Pretraining for Plant Cover Prediction

Cited by 4 publications

References 48 publications

Self-supervised maize kernel classification and segmentation for embryo identification

Self-supervised maize kernel classification and segmentation for embryo identification

Self-Supervised Maize Kernel Classification and Segmentation for Embryo Identification

Improving Data Efficiency for Plant Cover Prediction with Label Interpolation and Monte-Carlo Cropping

Contact Info

Product

Resources

About