報告題目: Hierarchically Gated Deep Networks for Semantic Segmentation
報告人：齊國君 博士
單位：美國中佛羅里達大學(xué)計算機系
報告時間：2016年7月11日（周一）上午10:00-11:00
報告地點：逸夫科教樓408會議室
報告摘要: Semantic segmentation aims to parse the scene structure of images by annotating the labels to each pixel so that images can be segmented into different regions. While image structures usually have various scales, it is difficult to use a single scale to model the spatial contexts for all
individual pixels. Multi-scale Convolutional Neural Networks (CNNs) and their variants have made striking success for modeling the global scene structure for an image. However, they are limited in labeling fine-grained local structures like pixels and patches, since spatial contexts might be blindly mixed up without appropriately customizing their scales. To address this challenge, we develop a novel paradigm of multi-scale deep network to model spatial contexts surrounding different pixels at various scales. It builds multiple layers of memory cells, learning feature representations for individual pixels at their customized scales by hierarchically absorbing relevant spatial contexts via memory gates between layers. Such Hierarchically Gated Deep Networks (HGDNs) can customize a suitable scale for each pixel, thereby delivering better performance on labeling scene structures of various scales. We conduct the experiments on two datasets, and show competitive results compared with the other multi-scale deep networks on the semantic segmentation task.
報告人簡介：齊國君博士是美國中佛羅里達大學(xué)計算機系助理教授。齊博士研究興趣包括面向多源異構(gòu)大數(shù)據(jù)的數(shù)據(jù)挖掘、智能信息處理等，并將所提出的方法應(yīng)用于社交網(wǎng)絡(luò)、醫(yī)療健康、金融系統(tǒng)等多個領(lǐng)域之中。齊博士在包括Preceedings of IEEE、TPAMI、TKDE、TIP、SIGKDD、ICML、CVPR、MM、WWW、ICDE、ICDM等眾多頂級期刊和會議發(fā)表超過六十篇論文，被引用超過2500次，H-index為24。齊博士獲得過ICDM2014最佳學(xué)生論文獎、ICDE2013最佳論文獎、MM2007最佳論文獎、兩次IBM學(xué)者獎、一次微軟學(xué)者獎。齊博士擔(dān)任了MMM2016大會共同主席，SIGKDD、CIKM、MM等多個頂級會議的領(lǐng)域主席，以及CVPR、ICCV等頂級會議的程序委員會委員。齊博士亦是IEEE Trans. Big Data、IEEE Trans. Multimedia等頂級期刊責(zé)任客座編委。
太陽集團tyc5997
TOP
