Segmentation algorithms are prone to make topological errors on fine-scale struc-tures, eg,
broken connections. We propose a novel method that learns to segment with correct …

In the past few years, convolutional neural networks (CNNs), particularly U-Net, have been
the prevailing technique in the medical image processing era. Specifically, the U-Net model …

Medical image segmentation is a fundamental task in the community of medical image
analysis. In this paper, a novel network architecture, referred to as Convolution, Transformer …

Deep learning methods have achieved impressive performance for multi-class medical
image segmentation. However, they are limited in their ability to encode topological …

Bottom-up segmentation based only on low-level cues is a notoriously difficult problem. This
difficulty has lead to recent top-down segmentation algorithms that are based on class …

Image Segmentation plays an essential role in computer vision and image processing with
various applications from medical diagnosis to autonomous car driving. A lot of …

Recent state-of-the-art image segmentation algorithms are mostly based on deep neural
networks, thanks to their high performance and fast computation time. However, these …

The paper introduces PaintSeg, a new unsupervised method for segmenting objects without
any training. We propose an adversarial masked contrastive painting (AMCP) process …

In the segmentation of fine-scale structures from natural and biomedical images, per-pixel
accuracy is not the only metric of concern. Topological correctness, such as vessel …

Delineation of curvilinear structures is an important problem in Computer Vision with
multiple practical applications. With the advent of Deep Learning, many current approaches …