DISC: Deep Image Saliency Computing via Progressive Representation Learning
DISC: Deep Image Saliency Computing via Progressive Representation Learning
复制标题
DISC：通过渐进式表示学习进行深度图像显着性计算
DOI：
10.1109/tnnls.2015.2506664
复制
发表时间：
2016-06-01
影响因子：
10.4
通讯作者：
Li, Xuelong
中科院分区：
文献类型：
--
作者：
Chen, Tianshui;Lin, Liang;Li, Xuelong
显著目标检测作为多个模式识别和图像处理任务中的重要组成部分或步骤越来越受到关注。虽然各种强大的显着性模型已被密集提出，他们通常涉及沉重的功能（或模型）工程的基础上先验（或假设）的对象和背景的属性。受最近开发的特征学习的有效性的启发，我们提供了一种新的深度图像显着性计算（DISC）框架，用于细粒度图像显着性计算。特别是，我们从粗层次和细层次的观察中对图像显著性进行建模，并利用深度卷积神经网络（CNN）以渐进的方式学习显著性表示。特别是，我们的显着性模型建立在两个堆叠的CNN上。第一个CNN通过将整个图像作为输入来生成粗略的显着性图，粗略地识别全局上下文中的显着区域。此外，我们在第一个CNN中集成了基于超像素的局部上下文信息，以细化粗糙级显着性图。在粗显着图的指导下，第二个CNN专注于局部上下文，以产生细粒度和准确的显着图，同时保留对象细节。对于测试图像，两个CNN协同进行一次显著性计算。我们的DISC框架能够在复杂背景中均匀地突出显示感兴趣的对象，同时保留良好的对象细节。在几个标准基准上进行的大量实验表明，DISC优于其他最先进的方法，并且在没有额外训练的情况下，它也可以很好地推广到数据集。DISC的可执行版本可在线获得：<;uri xlink：type=“simple”> http://vision.sysu.edu.cn/projects/DISC <;/uri>。
Salient object detection increasingly receives attention as an important component or step in several pattern recognition and image processing tasks. Although a variety of powerful saliency models have been intensively proposed, they usually involve heavy feature (or model) engineering based on priors (or assumptions) about the properties of objects and backgrounds. Inspired by the effectiveness of recently developed feature learning, we provide a novel deep image saliency computing (DISC) framework for fine-grained image saliency computing. In particular, we model the image saliency from both the coarse-and fine-level observations, and utilize the deep convolutional neural network (CNN) to learn the saliency representation in a progressive manner. In particular, our saliency model is built upon two stacked CNNs. The first CNN generates a coarse-level saliency map by taking the overall image as the input, roughly identifying saliency regions in the global context. Furthermore, we integrate superpixel-based local context information in the first CNN to refine the coarse-level saliency map. Guided by the coarse saliency map, the second CNN focuses on the local context to produce fine-grained and accurate saliency map while preserving object details. For a testing image, the two CNNs collaboratively conduct the saliency computing in one shot. Our DISC framework is capable of uniformly highlighting the objects of interest from complex background while preserving well object details. Extensive experiments on several standard benchmarks suggest that DISC outperforms other state-of-the-art methods and it also generalizes well across data sets without additional training. The executable version of DISC is available online: <;uri xlink:type="simple">http://vision.sysu.edu.cn/projects/DISC<;/uri>.