Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918110005559296 |
|---|---|
| author | Kniesel, Hannah Sick, Leon Payer, Tristan Bergner, Tim Devan, Kavitha Shaga Read, Clarissa Walther, Paul Ropinski, Timo |
| author_facet | Kniesel, Hannah Sick, Leon Payer, Tristan Bergner, Tim Devan, Kavitha Shaga Read, Clarissa Walther, Paul Ropinski, Timo |
| contents | Current state-of-the-art methods for object detection rely on annotated bounding boxes of large data sets for training. However, obtaining such annotations is expensive and can require up to hundreds of hours of manual labor. This poses a challenge, especially since such annotations can only be provided by experts, as they require knowledge about the scientific domain. To tackle this challenge, we propose a domain-specific weakly supervised object detection algorithm that only relies on image-level annotations, which are significantly easier to acquire. Our method distills the knowledge of a pre-trained model, on the task of predicting the presence or absence of a virus in an image, to obtain a set of pseudo-labels that can be used to later train a state-of-the-art object detection model. To do so, we use an optimization approach with a shrinking receptive field to extract virus particles directly without specific network architectures. Through a set of extensive studies, we show how the proposed pseudo-labels are easier to obtain, and, more importantly, are able to outperform other existing weak labeling methods, and even ground truth labels, in cases where the time to obtain the annotation is limited. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00563 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images Kniesel, Hannah Sick, Leon Payer, Tristan Bergner, Tim Devan, Kavitha Shaga Read, Clarissa Walther, Paul Ropinski, Timo Computer Vision and Pattern Recognition Current state-of-the-art methods for object detection rely on annotated bounding boxes of large data sets for training. However, obtaining such annotations is expensive and can require up to hundreds of hours of manual labor. This poses a challenge, especially since such annotations can only be provided by experts, as they require knowledge about the scientific domain. To tackle this challenge, we propose a domain-specific weakly supervised object detection algorithm that only relies on image-level annotations, which are significantly easier to acquire. Our method distills the knowledge of a pre-trained model, on the task of predicting the presence or absence of a virus in an image, to obtain a set of pseudo-labels that can be used to later train a state-of-the-art object detection model. To do so, we use an optimization approach with a shrinking receptive field to extract virus particles directly without specific network architectures. Through a set of extensive studies, we show how the proposed pseudo-labels are easier to obtain, and, more importantly, are able to outperform other existing weak labeling methods, and even ground truth labels, in cases where the time to obtain the annotation is limited. |
| title | Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.00563 |