Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images
This addresses the challenge of reducing annotation costs for experts in virology and microscopy, though it is incremental as it builds on existing weak supervision techniques.
The paper tackles the problem of expensive bounding box annotations for virus capsid detection in electron microscopy by proposing a weakly supervised method using only image-level labels, achieving performance that can outperform other weak labeling methods and even ground truth labels when annotation time is limited.
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.