Beyond KernelBoost

07/28/2014
by   Roberto Rigamonti, et al.
0

In this Technical Report we propose a set of improvements with respect to the KernelBoost classifier presented in [Becker et al., MICCAI 2013]. We start with a scheme inspired by Auto-Context, but that is suitable in situations where the lack of large training sets poses a potential problem of overfitting. The aim is to capture the interactions between neighboring image pixels to better regularize the boundaries of segmented regions. As in Auto-Context [Tu et al., PAMI 2009] the segmentation process is iterative and, at each iteration, the segmentation results for the previous iterations are taken into account in conjunction with the image itself. However, unlike in [Tu et al., PAMI 2009], we organize our recursion so that the classifiers can progressively focus on difficult-to-classify locations. This lets us exploit the power of the decision-tree paradigm while avoiding over-fitting. In the context of this architecture, KernelBoost represents a powerful building block due to its ability to learn on the score maps coming from previous iterations. We first introduce two important mechanisms to empower the KernelBoost classifier, namely pooling and the clustering of positive samples based on the appearance of the corresponding ground-truth. These operations significantly contribute to increase the effectiveness of the system on biomedical images, where texture plays a major role in the recognition of the different image components. We then present some other techniques that can be easily integrated in the KernelBoost framework to further improve the accuracy of the final segmentation. We show extensive results on different medical image datasets, including some multi-label tasks, on which our method is shown to outperform state-of-the-art approaches. The resulting segmentations display high accuracy, neat contours, and reduced noise.

READ FULL TEXT

page 3

page 9

page 11

page 14

page 16

page 17

page 19

page 21

research
05/30/2023

Hierarchical Multi-Instance Multi-Label Learning for Detecting Propaganda Techniques

Since the introduction of the SemEval 2020 Task 11 (Martino et al., 2020...
research
05/24/2022

Accuracy on In-Domain Samples Matters When Building Out-of-Domain detectors: A Reply to Marek et al. (2021)

We have noticed that Marek et al. (2021) try to re-implement our paper Z...
research
03/07/2022

Cartoon-texture evolution for two-region image segmentation

Two-region image segmentation is the process of dividing an image into t...
research
09/05/2018

Deep Relevance Ranking Using Enhanced Document-Query Interactions

We explore several new models for document relevance ranking, building u...
research
01/07/2020

The Ground Truth Trade-Off in Wearable Sensing Studies

Perez et al's study using the Apple Watch to identify atrial fibrillatio...
research
09/05/2017

Dynamic Multiscale Tree Learning Using Ensemble Strong Classifiers for Multi-label Segmentation of Medical Images with Lesions

We introduce a dynamic multiscale tree (DMT) architecture that learns ho...

Please sign up or login with your details

Forgot password? Click here to reset