paper-with-me

Papers

SynCellFactory: Generative Data Augmentation for Cell Tracking

2024-04-25 · Moritz Sturm, Lorenzo Cerrone, Fred A. Hamprecht

Cell tracking remains a pivotal yet challenging task in biomedical research. The full potential of deep learning for this purpose is often untapped due to the limited availability of comprehensive and varied training data sets. In this paper, we present SynCellFactory, a generative cell video augmentation. At the heart of SynCellFactory lies the ControlNet architecture, which has been fine-tuned to synthesize cell imagery with photorealistic accuracy in style and motion patterns. This technique enables the creation of synthetic yet realistic cell videos that mirror the complexity of authentic microscopy time-lapses. Our experiments demonstrate that SynCellFactory boosts the performance of well-established deep learning models for cell tracking, particularly when original training data is sparse.

📄 PDF Abstract BibTeX arXiv:2404.16421

Code (0)

등록된 구현이 없습니다.

Tasks

Cell TrackingData AugmentationDeep Learning

Similar Papers 제목 키워드 기반

On Improving an Already Competitive Segmentation Algorithm for the Cell Tracking Challenge - Lessons Learned

2021-06-28 · bioRxiv 2021 6 · Tim Scherr, Katharina Löffler, Oliver Neumann, Ralf Mikut

The virtually error-free segmentation and tracking of densely packed cells and cell nuclei is still a challenging task. Especially in low-resolution and low signal-to-noise-ratio microscopy images erroneously merged and …

Cell TrackingData AugmentationSegmentation

Object-Adaptive LSTM Network for Real-time Visual Tracking with Adversarial Data Augmentation

2020-02-07 · Yihan Du, Yan Yan, Si Chen, Yang Hua

In recent years, deep learning based visual tracking methods have obtained great success owing to the powerful feature representation ability of Convolutional Neural Networks (CNNs). Among these methods, classification-b…

Computational EfficiencyData AugmentationGeneral ClassificationGenerative Adversarial Network+2

Self-Training with Purpose Preserving Augmentation Improves Few-shot Generative Dialogue State Tracking

2022-11-17 · Jihyun Lee, Chaebin Lee, Yunsu Kim, Gary Geunbae Lee

In dialogue state tracking (DST), labeling the dataset involves considerable human labor. We propose a new self-training framework for few-shot generative DST that utilize unlabeled data. Our self-training method iterati…

Dialogue State Tracking

Cell Segmentation by Combining Marker-Controlled Watershed and Deep Learning

2020-04-03 · Filip Lux, Petr Matula

We propose a cell segmentation method for analyzing images of densely clustered cells. The method combines the strengths of marker-controlled watershed transformation and a convolutional neural network (CNN). We demonstr…

Cell DetectionCell SegmentationCell TrackingData Augmentation+2

Cell Tracking according to Biological Needs -- Strong Mitosis-aware Multi-Hypothesis Tracker with Aleatoric Uncertainty

2024-03-22 · Timo Kaiser, Maximilian Schier, Bodo Rosenhahn

Cell tracking and segmentation assist biologists in extracting insights from large-scale microscopy time-lapse data. Driven by local accuracy metrics, current tracking approaches often suffer from a lack of long-term con…

Cell TrackingMotion Estimationregression