首页 > 科学研究 > 学术看板 > 正文

面向显著性检测的深度特征探索

供稿:    责任编辑:安果    时间:2018-05-18    阅读:次

88125b大爆奖手机版 www.plumbing101.net 主讲人:张平平

报告时间:201852111:00

报告地点:基础教学楼A303

个人主页:https://scholar.google.com/citations?user=MfbIbuEAAAAJ&hl=zh-CN

报告题目:Delving into Deep Features for Saliency Detection

(面向显著性检测的深度特征探索)


报告摘要:

显著性检测已经在计算机视觉的应用中取得了巨大的成功。然而,视觉显著性的定义依赖于多种因素,很难用一种方式把所有的检测线索有效地统一起来,因此准确的显著性检测仍是一个未解难题。本次报告将介绍我们近期在显著性检测的方面的工作,特别是利用深度网络层次化的特点,探索不同深度全卷积网络模型,进而实现显著性检测的一系列方法。其中包含:1)自适应地聚合多水平卷积特征进行复杂场景的显著性物体检测;2)学习深度不确定性卷积特征,提升物体边界预测,进而提升物体检测性能;3)利用金字塔池化获取全局空间上下文特征,并进行逐步修正初始预测;4)根据图像的本征反射,将输入图像进行适当的无损反射分解,提取互补特征,进行显著物体检测。我们的方法在公开的数据集上均取得了优于其他算法的性能。

Saliency detection has achieved great success in computer vision applications. However, accurate saliency detection remains an unsolved problem because there are large variety of facts that cancontribute to define visual saliency, and it’s hard to combineall cues in an appropriate way. In this report, I will introduce our recent works on saliency detection, especially in different fully convolutional network models, which based on the hierarchical facts in deep neural networks. Our methods include:1) aggregating multi-level convolutionalfeature for salient object detection in complex scenes.2)learning deep uncertain convolutionalfeatures for boosting saliency detection, which encourage the confident boundaries of objects. 3) a stage-wise refinement model, in which a pyramid pooling moduleis applied for global context aggregation.4)based on the intrinsic reflectionof images, we decompose the input images into lossless reflection pairs to learn complementary features for saliency detection.Experimental evaluations on public benchmarksshow that our proposed methods compares favorably againstthe state-of-the-art approaches.


报告人简介:

张平平博士现为澳大利亚视觉技术研究中心(ACVT)研究员. 他分别于2012年、2018年在河南师范大学、大连理工大学获得理学学士、工学博士学位。师从大连理工大学卢湖川教授,其主要研究兴趣为计算机视觉与机器学习。他已在国际计算机视觉和人工智能顶级会议(如ICCV,ECCV,IJCAI)以及期刊(如TIP,TCSVT,PR)上发表论文十数篇,并担任多个会议及期刊的审稿人,如CVPR,ICCV,ECCV,IJCAI,TPAMI,IJCV,TIP等。

Dr. Pingping Zhangis a research in Australian Centre of Visual Technology. In 2012 and 2018, He received the B.S. and Ph.D degree from Henan Normal University (HNU) and Dalian University of Technology (DUT), respectively. His supervisor is Prof. Huchuan Lu. His main research interests are in computer vision and machine learning. He has published more than 10 papers in top conferences/journals of computer vision and artificial intelligence, including ICCV, ECCV,IJCAI,TIP TCSVT,PR,etc. He also serves as the reviewer CVPR,ICCV,ECCV,IJCAI,TPAMI,IJCV,TIP,etc..