计算机科学
卷积神经网络
目标检测
人工智能
简单
图层(电子)
突出
特征(语言学)
模式识别(心理学)
分割
GSM演进的增强数据速率
探测器
边缘检测
图像(数学)
深度学习
比例(比率)
图像分割
特征提取
图像处理
物理
哲学
电信
认识论
有机化学
化学
量子力学
语言学
作者
Qibin Hou,Ming‐Ming Cheng,Xiaowei Hu,Ali Borji,Zhuowen Tu,Philip H. S. Torr
标识
DOI:10.1109/cvpr.2017.563
摘要
Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs). Semantic segmentation and saliency detection algorithms developed lately have been mostly based on Fully Convolutional Neural Networks (FCNs). There is still a large room for improvement over the generic FCN models that do not explicitly deal with the scale-space problem. Holisitcally-Nested Edge Detector (HED) provides a skip-layer structure with deep supervision for edge and boundary detection, but the performance gain of HED on saliency detection is not obvious. In this paper, we propose a new saliency method by introducing short connections to the skip-layer structures within the HED architecture. Our framework provides rich multi-scale feature maps at each layer, a property that is critically needed to perform segment detection. Our method produces state-of-the-art results on 5 widely tested salient object detection benchmarks, with advantages in terms of efficiency (0.08 seconds per image), effectiveness, and simplicity over the existing algorithms.
科研通智能强力驱动
Strongly Powered by AbleSci AI