Cell Detection from Imperfect Annotation by Pseudo Label Selection Using P-classification

Fujii, Kazuma; Suehiro, Daiki; Nishimura, Kohei; Bise, Ryoma

doi:10.1007/978-3-030-87237-3_41

Cited by 7 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Related Workmentioning

confidence: 99%

“…Several related methods use CNNs [3,5,6,9,12,22,24] or combine CNNs with classical image analysis approaches [17] for cell detection in biomedical microscopy images. Amongst these methods, two approaches are common: (i) to perform cell detection by predicting a heatmap for cell positions [3,12,24] or (ii) to perform cell detection by predicting the coordinates of bounding boxes for cells [5,6,9]. The heatmap-based methods are well suited for cell counting, but are unsuitable for morphological studies since they only predict where cells are located and do not provide information on the cell dimensions.…”

Section: Related Workmentioning

confidence: 99%

“…However, the bounding box-based methods use a cascade of two CNNs and are therefore not end-to-end trainable. To deal with sparsely annotated or small datasets, semi-supervised learning [3,12] or pre-training with synthetic data [24] is used. Thus complicating the training process, since pseudolabels must be iteratively generated or synthetic data must be created in advance.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

CellCentroidFormer: Combining Self-attention and Convolution for Cell Detection

Wagner¹,

Rohr²

2022

Preprint

View full text Add to dashboard Cite

Cell detection in microscopy images is important to study how cells move and interact with their environment. Most recent deep learning-based methods for cell detection use convolutional neural networks (CNNs). However, inspired by the success in other computer vision applications, vision transformers (ViTs) are also used for this purpose. We propose a novel hybrid CNN-ViT model for cell detection in microscopy images to exploit the advantages of both types of deep learning models. We employ an efficient CNN, that was pre-trained on the ImageNet dataset, to extract image features and utilize transfer learning to reduce the amount of required training data. Extracted image features are further processed by a combination of convolutional and transformer layers, so that the convolutional layers can focus on local information and the transformer layers on global information. Our centroid-based cell detection method represents cells as ellipses and is end-to-end trainable. Furthermore, we show that our proposed model can outperform fully convolutional one-stage detectors on four different 2D microscopy datasets. Code is available at: https://github.com/roydenwa/cell-centroid-former

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

CellCentroidFormer: Combining Self-attention and Convolution for Cell Detection

Wagner¹,

Rohr²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Therefore, the acquisition of the perfect annotation is time-consuming and labour-intensive. To decrease the dependency on perfect annotation, numerous research works have studied the different scenarios of imperfect annotation, such as incomplete annotation [33,34], unreliable labels [35], and incremental new categories [36]. However, the incomplete annotation problem of insulator defect detection is not thoroughly investigated.…”

Section: Introductionmentioning

confidence: 99%

Electrical insulator defect detection with incomplete annotations and imbalanced samples

Pang,

Lei,

Zeng

2024

IET Generation Trans & Dist

View full text Add to dashboard Cite

Insulators are one of the key components in high‐voltage power systems that prevent transmission lines from grounding. Since they are exposed to different kinds of harsh environments and climates, periodic inspection is indispensable for the safety and high quality of power grid. Nowadays, unmanned aerial vehicle (UAV) inspection is more widely used, facilitating incorporation of convolutional neural network‐based detectors in the insulator detection task. However, these methods are generally based on the assumption that the image samples are balanced among different categories and possess completely ideal annotations. The problem of sample imbalance or incomplete annotation is rarely investigated in depth for insulator defect detection. Here, insulator defect detection with imbalanced data and incomplete annotations is focused on. The proposed framework, named Pi‐index, introduces positive unlabelled (PU) learning to solve the problem of incomplete annotation and designs a novel index the class prior, which is a key parameter in PU learning. Moreover, focal loss is integrated in our framework to alleviate the effect of sample imbalance. Experiment results demonstrate that the proposed framework achieves better performance than the baseline methods in situations of sample imbalance and missing annotation.

show abstract

“…Therefore, the acquisition of the perfect annotation is time-consuming and labor-intensive. To decrease the dependency on perfect annotation, numerous research works have studied the different scenarios of imperfect annotation, such as incomplete annotation [33], [34], unreliable labels [35], and incremental new categories [36]. However, the incomplete annotation problem of insulator defect detection is not thoroughly investigated.…”

Section: Introductionmentioning

confidence: 99%

Electrical insulator defect detection with incomplete annotations and imbalanced samples

Pang,

Lei,

zeng

2023

Preprint

View full text Add to dashboard Cite

Insulators are one of the key components in high-voltage power systems that prevent transmission lines from grounding. Since they are exposed to different kinds of harsh environments and climates, periodic inspection is indispensable for the safety and high quality of power grid. Nowadays, Unmanned Aerial Vehicle (UAV) inspection is more widely used, facilitating incorporation of CNN-based detectors in the insulator detection task. However, these methods are generally based on the assumption that the image samples are balanced among different categories and possess completely ideal annotations. The problem of sample imbalance or incomplete annotation is rarely investigated in depth for insulator defect detection. In this paper, we focus on insulator defect detection with imbalanced data and incomplete annotations. Our proposed framework, named Pi-Index, introduces Positive Unlabeled (PU) learning to solve the problem of incomplete annotation and designs a novel index the class prior, which is a key parameter in PU learning. Moreover, focal loss is integrated in our framework to alleviate the effect of sample imbalance. Experiment results demonstrate that the proposed framework achieves better performance than the baseline methods in situations of sample imbalance and missing annotation.

show abstract

Cell Detection from Imperfect Annotation by Pseudo Label Selection Using P-classification

Cited by 7 publications

References 18 publications

CellCentroidFormer: Combining Self-attention and Convolution for Cell Detection

CellCentroidFormer: Combining Self-attention and Convolution for Cell Detection

Electrical insulator defect detection with incomplete annotations and imbalanced samples

Electrical insulator defect detection with incomplete annotations and imbalanced samples

Contact Info

Product

Resources

About