VIP內容

題目:Image Segmentation Using Deep Learning: A Survey

摘要:

圖像分割是圖像處理和計算機視覺領域的一個重要課題,其應用領域包括場景理解、醫學圖像分析、機器人感知、視頻監控、增強現實和圖像壓縮等。文獻中已經發展了各種圖像分割算法。最近,由於深度學習模型在廣泛的視覺應用中取得了成功,已經有大量的工作致力於開發使用深度學習模型的圖像分割方法。在本次調查中,我們對撰寫本文時的文獻進行了全麵的回顧,涵蓋了語義和實例級分割的廣泛的開創性著作,包括全卷積像素標記網絡,編碼器-解碼器架構,多尺度和基於金字塔的方法,遞歸網絡,視覺注意力模型,以及在對抗性環境下的生成模型。我們調查了這些深度學習模型的相似性、優勢和挑戰,研究了最廣泛使用的數據集,報告了性能,並討論了該領域未來的研究方向。

成為VIP會員查看完整內容
0
18
1

最新論文

Intrusion Prevention Systems (IPS), have long been the first layer of defense against malicious attacks. Most sensitive systems employ instances of them (e.g. Firewalls) to secure the network perimeter and filter out attacks or unwanted traffic. A firewall, similar to classifiers, has a boundary to decide which traffic sample is normal and which one is not. This boundary is defined by configuration and is managed by a set of rules which occasionally might also filter normal traffic by mistake. However, for some applications, any interruption of the normal operation is not tolerable e.g. in power plants, water distribution systems, gas or oil pipelines, etc. In this paper, we design a learning firewall that receives labelled samples and configures itself automatically by writing preventive rules in a conservative way that avoids false alarms. We design a new family of classifiers, called $\mathfrak{z}$-classifiers, that unlike the traditional ones which merely target accuracy, rely on zero false-positive as the metric for decision making. First, we analytically show why naive modification of current classifiers like SVM does not yield acceptable results and then, propose a generic iterative algorithm to accomplish this goal. We use the proposed classifier with CART at its heart to build a firewall for a Power Grid Monitoring System. To further evaluate the algorithm, we additionally test it on KDD CUP'99 dataset. The results confirm the effectiveness of our approach.

0
0
0
下載
預覽
Top