Knowledge Commons of Institute of Automation,CAS
Objectness-aware Semantic Segmentation | |
Yuhang Wang; Jing Liu; Yong Li; Junjie Yan; Hanqing Lu | |
2016 | |
会议名称 | ACM Multimedia |
会议录名称 | Proceedings of the 2016 ACM on Multimedia Conference |
会议日期 | October 15 – 19 , 2016 |
会议地点 | Amsterdam, Netherlands |
摘要 | Recent advances in semantic segmentation are driven by the success of fully convolutional neural network (FCN). However, the coarse label map from the network and the object discrimination ability for semantic segmentation weaken the performance of those FCN-based models. To address these issues, we propose an objectness-aware semantic segmentation framework (OA-Seg) by jointly learning an object proposal network (OPN) and a lightweight deconvolutional neural network (Light-DCNN). First, OPN is learned based on a fully convolutional architecture to simultaneously predict object bounding boxes and their objectness scores. Second, we design a Light-DCNN to provide a finer upsampling way than FCN. The Light-DCNN is constructed with convolutional layers in VGG-net and their mirrored deconvolutional structure, where all fully-connected layers are removed. And hierarchical classification layers are added to multi-scale deconvolutional features to introduce more contextual information for pixel-wise label prediction. Compared with previous works, our approach performs an obvious decrease on model size and convergence time. Thorough evaluations are performed on the PASCAL VOC 2012 benchmark, and our model yields impressive results on its validation data (70.3% mean IoU) and test data (74.1% mean IoU). |
关键词 | Deconvolutional Neural Network Semantic Segmentation |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/13440 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Jing Liu |
作者单位 | 中国科学院自动化研究所 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yuhang Wang,Jing Liu,Yong Li,et al. Objectness-aware Semantic Segmentation[C],2016. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Objectness-aware Sem(1069KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论