For reality applications of semantic segmentation, inference speed and memory usage are two important factors. To address these challenges, we propose a lightweight feature pyramid encoding network (FPENet) for segmentation with good trade-off between accuracy speed. We use series (FPE) blocks to encode context at multiple scales in the encoder. Each FPE block consists different depthwise dilat...

Feature models (FM) are a way for modeling and describing the product family of specific domain. They are widely used for describing the requirements in the domain engineering as it describes the commonalities and the differences of related products in specific domain. Currently the research in the feature model analysis and the validation of it focus on capturing the inconsistencies of the fea...

In few-shot unsupervised domain adaptation (FS-UDA), most existing methods followed the learning (FSL) to leverage low-level local features (learned from conventional convolutional models, e.g., ResNet) for classification. However, goal of FS-UDA and FSL are relevant yet distinct, since aims classify samples in target rather than source domain. We found that insufficient FS-UDA, which could int...

In this paper, we propose an access control method with a secret key for semantic segmentation models the first time so that unauthorized users without cannot benefit from performance of trained models. The enables us not only to provide high authorized but also degrade users. We point out that, application segmentation, conventional methods which use encrypted images classification tasks are d...

In this paper, a multi-level image representation model is developed and used to mine semantic feature hidden in the original remote sensing image. This model is consisted of three levels : region level, region feature level and semantic level. The first two levels aim at represent image content by using region feature. Semantic level aims at extracting hidden semantic feature. At last, interes...

The undo mechanism is an essential feature in collaborative editing systems. Most popular semantic wikis support a revert feature, some provide an undo feature to remove any modification at any time. However this undo feature does not always succeed. Supporting the undo mechanism for P2P semantic wikis has never been tackled. In this paper, we present an undo approach for Swooki, the first P2P ...

Phishing is one of the luring techniques used to exploit personal information. A phishing webpage detection system (PWDS) extracts features to determine whether it is a phishing webpage or not. Selecting appropriate features improves the performance of PWDS. Performance criteria are detection accuracy and system response time. The major time consumed by PWDS arises from feature extraction that ...