Medical image segmentation methods based on deep learning have made remarkable
progress. However, such existing methods are sensitive to data distribution. Therefore, slight …

In this paper, we present novel strategies for optimizing the performance of many binary
image processing algorithms. These strategies are collected in an open-source framework …

Detecting object skeletons in natural images presents challenges due to varied object
scales and complex backgrounds. The skeleton is a highly compressing shape …

Given its nature of statistical inference, machine learning methods incline to downplay
relatively rare events. But in many applications statistical outliers carry disproportional …

Geometric shape understanding provides an intuitive representation of object shapes.
Skeleton is typical geometrical information. Lots of traditional approaches are developed for …

Few-shot class-incremental learning (FSCIL) aims to continually learn novel data with
limited samples. One of the major challenges is the catastrophic forgetting problem of old …

Orthogonality regularization has proven effective in improving the precision, convergence
speed and the training stability of CNNs. Here, we propose a novel Orthogonal Dictionary …

Object skeleton detection requires the convolutional neural networks to recognize objects
and their parts in the cluttered background, overcome the image definition degradation …

Visual long-range interaction refers to modeling dependencies between distant feature
points or blocks within an image, which can significantly enhance the model's robustness …