当前位置: X-MOL 学术Vis. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Image saliency detection via multi-scale iterative CNN
The Visual Computer ( IF 3.5 ) Pub Date : 2019-08-06 , DOI: 10.1007/s00371-019-01734-2
Kun Huang , Shenghua Gao

Salient object detection has received increasingly more attention and achieved significant progress lately due to the powerful features learned by deep convolutional neural networks (CNNs). In this work, we propose a multi-scale iterative CNN for salient object detection, which has two complementary subnetworks at different spatial scales. For each subnetwork, we augment the CNN structures with an iterative learning process to learn the saliency map, where early stages of the CNN give a rough estimate of the saliency map and the remaining errors are gradually learned to refine the saliency map. By merging predictions of the two subnetworks, the training error can be reduced significantly and the estimated saliency map becomes more accurate. Unlike some previous CNN-based methods which often rely on superpixel segmentations, the proposed model is fully CNN and hence can estimate the saliency map much more efficiently. Extensive experiments on standard benchmarks demonstrate that our method outperforms some of the state-of-the-art methods in terms of both accuracy and speed and achieves as good performance as some recent state-of-the-art end-to-end methods under fair settings.

中文翻译:

通过多尺度迭代CNN进行图像显着性检测

由于深度卷积神经网络(CNN)学习到的强大特征,显着物体检测最近受到越来越多的关注并取得了重大进展。在这项工作中,我们提出了一种用于显着目标检测的多尺度迭代 CNN,它在不同的空间尺度上具有两个互补的子网络。对于每个子网络,我们通过迭代学习过程来增强 CNN 结构以学习显着图,其中 CNN 的早期阶段对显着图进行粗略估计,并逐渐学习剩余的错误以细化显着图。通过合并两个子网络的预测,可以显着减少训练误差,估计的显着图变得更加准确。与之前的一些基于 CNN 的方法通常依赖于超像素分割不同,所提出的模型完全是 CNN,因此可以更有效地估计显着图。在标准基准上的大量实验表明,我们的方法在准确性和速度方面都优于一些最先进的方法,并且在以下条件下实现了与一些最新的最先进的端到端方法一样好的性能公平的设置。
更新日期:2019-08-06
down
wechat
bug