Mixup provides interpolated training samples and allows the model to obtain smoother decision boundaries for better generalization. The idea can be naturally applied domain adaptation task, where we mix source target domain-mixed adaptation. However, extension of from classification segmentation (i.e., structured output) is nontrivial. This paper systematically studies impact mixup under adapti...

Unsupervised domain adaptation (UDA) aims to adapt a model of the labeled source an unlabeled target domain. Existing UDA-based semantic segmentation approaches always reduce shifts in pixel level, feature and output level. However, almost all them largely neglect contextual dependency, which is generally shared across different domains, leading less-desired performance. In this paper, we propo...

A new self-organizing map with variable topology is introduced for image segmentation. The proposed network, called Local Adaptive Receptive Field Self-organizing Map (LARFSOM-RBF), is a two-stage network capable of both color and border segment images. The color segmentation stage is responsibility of LARFSOM which is characterized by adaptive number of nodes, fast convergence and variable top...

ÐAn adaptive image segmentation scheme is proposed employing the Delaunay triangulation for image splitting. The tessellation grid of the Delaunay triangulation is adapted to the semantics of the image data by combining region and edge information. To achieve robustness against imaging conditions (e.g., shading, shadows, illumination, and highlights), photometric invariant similarity measures, ...

Introduction Breast cancer is one of the most common types of cancer among women.  Early detection of breast cancer is the key to reducing the associated mortality rate. The presence of microcalcifications clusters (MCCs) is one of the earliest signs of breast cancer. Due to poor imaging contrast of mammograms and noise contamination, radiologists may overlook some diagnostic signs, specially t...

This paper presents a Chinese word segmentation system which can adapt to different domains and standards. We first present a statistical framework where domain-specific words are identified in a unified approach to word segmentation based on linear models. We explore several features and describe how to create training data by sampling. We then describe a transformation-based learning method u...

ADAPTIVE REGISTRATION AND ATLAS BASED SEGMENTATION

The capability of the adaptive optics to correct for the segmentation error is analyzed in terms of the residual wavefront RMS and the power spectral density of the phase. The analytical model and the end-to-end simulation give qualitatively equal results justifying the significance of the geometrical matching between segmentation geometry and the actuators/subaperture distribution of the adapt...