Objectness Region Enhancement Networks for Scene Parsing

Objectness Region Enhancement Networks for Scene Parsing
复制标题

用于场景解析的对象区域增强网络

DOI:
10.1007/s11390-017-1751-x
复制
发表时间:
2017-07
影响因子:
0.7
通讯作者:
Dan Li
Dan Li
中科院分区:
--
文献类型:
--
作者:
Xinyu Ou;Ping Li;Hefei Ling;Si Liu;Tianjiang Wang;Dan Li

文献摘要

参考文献

相似文献

语义分割近年来取得了快速的进展,但现有的方法只关注于识别对象或实例。在这项工作中,我们的目标是通过深度学习来解决场景语义理解的任务。与许多现有的方法不同,我们的方法侧重于提出一些技术来改进现有的算法,而不是提出一个全新的框架。客观性增强是第一个有效的技术。它利用检测模块产生具有类别概率的对象区域建议,并将这些区域直接用于分析特征图的权重。“额外背景”范畴作为一个特定的范畴,常被附加到范畴空间中,以提高语义和实例切分任务的分析效果。在场景分析任务中,额外的背景类别仍然有利于改进模型的训练。然而,在推理中,一些像素可能被分配到这个不存在的类别中。提出了黑洞填充技术,以避免错误的分类。为了验证这两种技术,我们将它们集成到一个语法分析框架中,生成语法分析结果。我们把这个统一的框架称为对象增强网络(OENet)。与以前的工作相比,我们提出的OENet系统有效地提高了SceneParse 150场景解析数据集上的原始模型的性能,在验证集上达到38.4 mIoU(mean intersectionover-union)和77.9%的准确率,而无需组装多个模型。它的有效性也在Cityscapes数据集上得到了验证。
Semantic segmentation has recently witnessed rapid progress, but existing methods only focus on identifying objects or instances. In this work, we aim to address the task of semantic understanding of scenes with deep learning. Different from many existing methods, our method focuses on putting forward some techniques to improve the existing algorithms, rather than to propose a whole new framework. Objectness enhancement is the first effective technique. It exploits the detection module to produce object region proposals with category probability, and these regions are used to weight the parsing feature map directly. “Extra background” category, as a specific category, is often attached to the category space for improving parsing result in semantic and instance segmentation tasks. In scene parsing tasks, extra background category is still beneficial to improve the model in training. However, some pixels may be assigned into this nonexistent category in inference. Black-hole filling technique is proposed to avoid the incorrect classification. For verifying these two techniques, we integrate them into a parsing framework for generating parsing result. We call this unified framework as Objectness Enhancement Network (OENet). Compared with previous work, our proposed OENet system effectively improves the performance over the original model on SceneParse150 scene parsing dataset, reaching 38.4 mIoU (mean intersectionover-union) and 77.9% accuracy in the validation set without assembling multiple models. Its effectiveness is also verified on the Cityscapes dataset.
低复杂度 H.265/HEVC 编码器基于内容属性的快速运动估计
DOI: 10.1109/tbc.2016.2580920
发表时间: 2016-06
影响因子: 4.5
作者:
Pan Zhaoqing;Lei Jianjun;Zhang Yun;Sun Xingming;Kwong Sam
通讯作者: Kwong Sam
DOI: 10.1109/tpami.2017.2708714
发表时间: 2018-06-01
影响因子: 23.6
作者:
Lin, Guosheng;Shen, Chunhua;Reid, Ian
通讯作者: Reid, Ian
DOI: 10.1109/cvpr.2017.114
发表时间: 2016-11
期刊: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子: --
作者:
Si Liu;Changhu Wang;Ruihe Qian;Han Yu;Renda Bao;Yao Sun
通讯作者: Si Liu;Changhu Wang;Ruihe Qian;Han Yu;Renda Bao;Yao Sun
DOI: 10.1145/2393347.2396470
发表时间: 2012-10
期刊: Proceedings of the 20th ACM international conference on Multimedia
影响因子: --
作者:
Si Liu;Tam V. Nguyen;Jiashi Feng;Meng Wang;Shuicheng Yan
通讯作者: Si Liu;Tam V. Nguyen;Jiashi Feng;Meng Wang;Shuicheng Yan
DOI: --
发表时间: 2016-04
期刊: ArXiv
影响因子: --
作者:
Si Liu;Xinyu Ou;Ruihe Qian;Wei Wang;Xiaochun Cao
通讯作者: Si Liu;Xinyu Ou;Ruihe Qian;Wei Wang;Xiaochun Cao