CNN for saliency detection with low-level feature integration

详细信息    查看全文

• 作者：Hongyang Li^aAuthor Vitae ; Jiang Chen^b ; ^{steve.chen@sap.com}Author Vitae ; Huchuan Lu^cAuthor Vitae ; Zhizhen Chi^cAuthor Vitae
• 关键词：Saliency detection ; Convolutional neural networks
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：22 February 2017
• 年：2017
• 卷：226
• 期：Complete
• 页码：212-220
• 全文大小：1359 K
• 卷排序：226

文摘

Propose a novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images. Utilise the advantage of convolutional neural networks to automatically learn the high-level features that capture the structured information and semantic context in the image. Experiments on three challenging benchmarks demonstrate our algorithm to be effective and superior than most low-level oriented state-of-the-arts in terms of precision-recall curves, F-measure and mean absolute errors.