论文笔记：MICCAI2018 Cell Detection with Star-convex Polygons

Motivation：

especially appealing for images of very crowded cells

bottom-up approach

to first classify every pixel into semantic classes (such as cell or background) and then group pixels of the same class into individual instances.

每个像素分类为语义类，然后将同一类的像素分组为单个实例。

problematic for images of very crowded cell nuclei, since only a few mis-classified pixels can cause bordering but distinct cell instances to be fused.

对于非常拥挤的细胞核图像来说，这是一个问题，因为只有少数分类错误的像素会导致接近但不同的细胞实例融合

top-down approach

first localize individual cell instances with a rough shape representation and then refine the shape in an additional step

首先使用粗略的形状表示本地化单个单元实例，然后在附加步骤中优化形状

NMS can be problematic if the objects of interest are poorly represented by their axis-aligned bounding boxes. While this can be mitigated by using rotated bounding boxes [10], it is still necessary to refine the box shape to accurately describe objects such as cell nuclei.

如果感兴趣的对象不能很好地用轴对齐的边界框表示，NMS可能会出现问题。虽然这可以通过使用旋转的边界框来缓解[10]，但仍有必要细化框的形状，以准确描述诸如细胞核之类的对象。

Method：

针对the single object class cell nuclei，predicts a shape representation

图像中每个点(i,j),分别回归star-convex polygon distances(k)和object probabilities(d).

object probabilities (d_(i,j)): 点(i,j) 的euclidean distance to the nearest background pixel。每个点一个距离

star-convex polygon distances (k_(i,j))：属于同一个物体类别的点(i,j)沿radial direction到物体边界的最远距离。每个点有k个距离

loss：

For the predicted object probabilities, binary cross-entropy loss

For the polygon distances, mean absolute error loss weighted by the ground truth object probabilities

关于star-convex polygon distances与radital detection：

在CVPR2017 Straight to Shapes: Real-time Detection of Encoded Shapes中引入，但不适合，如下图。但是这种形状表征很适合细胞。

论文笔记：MICCAI2018 Cell Detection with Star-convex Polygons相关推荐

论文笔记：Object Detection in 20 Years: A Surve（目标检测20年研究综述）
文章目录 1.介绍 2.目标检测的20年发展历程 2.1.目标检测路线 2.1.1.里程碑:传统检测器 2.1.2.基于CNN的两阶段检测器 2.1.3.基于CNN的单阶段检测器 2.2.目标检测数据 ...
[论文笔记]On the Detection of Digital Face Manipulation
On the Detection of Digital Face Manipulation 这篇文章主要介绍一种attention机制的深度伪造鉴别和伪造区域定位的方法. 创新点(主要贡献) 制作了一 ...
论文笔记 Multiple Instance Detection Network with Online Instance Classifier Refinement - CVPR 2017
Multiple Instance Detection Network with Online Instance Classifier Refinement 华中科大Peng Tang, Xingga ...
【目标检测】论文笔记Arbitrary-Oriented Object Detection with Circular Smooth Label（2020）
目录前情提要: 解决方案 Regression-based Rotation Detection Method Boundary Problem of Regression Method Some ...
论文笔记 | Self-organized Text Detection with Minimal Post-processing via Border Learning
论文链接:http://openaccess.thecvf.com/content_ICCV_2017/papers/Wu_Self-Organized_Text_Detection_ICCV_201 ...
论文笔记——Camouflaged Object Detection
文章目录 1 简介 2 网络结构 2.1 Search Module (SM) 2.2 Identification Module (IM) 2020年CVPR的一篇文章,文章名为"伪装物体 ...
论文笔记 Object-Aware Instance Labeling for Weakly Supervised Object Detection - ICCV 2019
Object-Aware Instance Labeling for Weakly Supervised Object Detection Kosugi ICCV, 2019 (PDF) (Citat ...
[论文笔记] DETR 论文笔记
DETR 论文笔记 End-to-End Object Detection with Transformers(ECCV 2020) 摘要引言相关工作集合预测 DETR 模型集合预测损失(Ob ...
Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion论文笔记
CVPR2021论文笔记题目:Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Mod ...

论文笔记：MICCAI2018 Cell Detection with Star-convex Polygons

论文笔记：MICCAI2018 Cell Detection with Star-convex Polygons相关推荐

最新文章

热门文章