超氧化物歧化酶(Superoxide dismutase,SOD)是生物体系中抗氧化酶系的重要组成成员,广泛分布在微生物、植物和动物体内

VIP内容

论文题目: Salient Object Detection in the Deep Learning Era: An In-Depth Survey

论文摘要: 作为计算机视觉中的一个重要问题,图像中的显著目标检测(SOD)近年来得到了越来越多的研究。最近在超氧化物歧化酶方面的进展主要是基于深度学习的解决方案(称为深超氧化物歧化酶)。为了便于深入理解深层SODs,本文提供了一个全面的综述,涵盖了从算法分类到未解决的开放问题的各个方面。特别是,我们首先从网络结构、监控级别、学习范式和对象/实例级别检测等不同角度对深度超氧化物歧化酶算法进行了综述。在此基础上,总结了现有的SOD评价数据集和指标体系。然后,在前人工作的基础上,认真编写了一个完整的SOD方法的基准测试结果,并对对比结果进行了详细的分析。另外,通过构造一个新的具有丰富属性标注的SOD数据集,研究了不同属性下的SOD算法的性能,这在以前的研究中是很少的。我们首次在现场进一步分析了deep-SOD模型的鲁棒性和可转移性。我们还研究了输入扰动的影响,以及现有SOD数据集的通用性和硬度。最后,讨论了超氧化物歧化酶存在的问题和挑战,并指出了未来可能的研究方向。

成为VIP会员查看完整内容
Salient Object Detection in the Deep Learning Era An In-Depth Survey.pdf
0
20

最新内容

In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD). The architecture of our U$^2$-Net is a two-level nested U-structure. The design has the following advantages: (1) it is able to capture more contextual information from different scales thanks to the mixture of receptive fields of different sizes in our proposed ReSidual U-blocks (RSU), (2) it increases the depth of the whole architecture without significantly increasing the computational cost because of the pooling operations used in these RSU blocks. This architecture enables us to train a deep network from scratch without using backbones from image classification tasks. We instantiate two models of the proposed architecture, U$^2$-Net (176.3 MB, 30 FPS on GTX 1080Ti GPU) and U$^2$-Net$^{\dagger}$ (4.7 MB, 40 FPS), to facilitate the usage in different environments. Both models achieve competitive performance on six SOD datasets. The code is available: https://github.com/NathanUA/U-2-Net.

0
0
下载
预览

最新论文

In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD). The architecture of our U$^2$-Net is a two-level nested U-structure. The design has the following advantages: (1) it is able to capture more contextual information from different scales thanks to the mixture of receptive fields of different sizes in our proposed ReSidual U-blocks (RSU), (2) it increases the depth of the whole architecture without significantly increasing the computational cost because of the pooling operations used in these RSU blocks. This architecture enables us to train a deep network from scratch without using backbones from image classification tasks. We instantiate two models of the proposed architecture, U$^2$-Net (176.3 MB, 30 FPS on GTX 1080Ti GPU) and U$^2$-Net$^{\dagger}$ (4.7 MB, 40 FPS), to facilitate the usage in different environments. Both models achieve competitive performance on six SOD datasets. The code is available: https://github.com/NathanUA/U-2-Net.

0
0
下载
预览
Top