无监督层次表征学习模型及其在遥感影像解译中的应用
项目来源
项目主持人
项目受资助机构
立项年度
立项时间
项目编号
研究期限
项目级别
受资助金额
学科
学科代码
基金类别
参与者
参与机构
项目受资助省
项目结题报告(全文)
1.Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling
- Liu, Hongying ; Zhao, Peng ; Ruan, Zhubo ; Shang, Fanhua ; Liu, Yuanyuan
- 《35th AAAI Conference on Artificial Intelligence, AAAI 2021》
- 2021年
- 会议
2.Supervised Edge Attention Network for Accurate Image Instance Segmentation
- 关键词：
- Computer vision;Convolution;Image segmentation;Attention mechanisms;Background noise;Baseline models;Bounding box
- Chen, Xier;Lian, Yanchao;Jiao, Licheng;Wang, Haoran;Gao, YanJie;Lingling, Shi
- 《16th European Conference on Computer Vision, ECCV 2020》
- 2020年
- August 23, 2020 - August 28, 2020
- Glasgow, United kingdom
- 会议
Effectively keeping boundary of the mask complete is important in instance segmentation. In this task, many works segment instance based on a bounding box from the box head, which means the quality of the detection also affects the completeness of the mask. To circumvent this issue, we propose a fully convolutional box head and a supervised edge attention module in mask head. The box head contains one new IoU prediction branch. It learns association between object features and detected bounding boxes to provide more accurate bounding boxes for segmentation. The edge attention module utilizes attention mechanism to highlight object and suppress background noise, and a supervised branch is devised to guide the network to focus on the edge of instances precisely. To evaluate the effectiveness, we conduct experiments on COCO dataset. Without bells and whistles, our approach achieves impressive and robust improvement compared to baseline models. Code is at https://github.com//IPIU-detection/SEANet. © 2020, Springer Nature Switzerland AG.
...3.AttAN: Attention adversarial networks for 3D point cloud semantic segmentation
- 关键词：
- Semantic Web;Semantics;High dimensional spaces;High order correlation;Multi-scale features;Segmentation accuracy;Segmentation results;Semantic segmentation;State-of-the-art methods;Three dimensional space
- Zhang, Gege;Ma, Qinghua;Jiao, Licheng;Liu, Fang;Sun, Qigong
- 《29th International Joint Conference on Artificial Intelligence, IJCAI 2020》
- 2020年
- January 1, 2021
- Yokohama, Japan
- 会议
3D point cloud semantic segmentation has attracted wide attention with its extensive applications in autonomous driving, AR/VR, and robot sensing fields. However, in existing methods, each point in the segmentation results is predicted independently from each other. This property causes the non-contiguity of label sets in three-dimensional space and produces many noisy label points, which hinders the improvement of segmentation accuracy. To address this problem, we first extend adversarial learning to this task and propose a novel framework Attention Adversarial Networks (AttAN). With high-order correlations in label sets learned from the adversarial learning, segmentation network can predict labels closer to the real ones and correct noisy results. Moreover, we design an additive attention block for the segmentation network, which is used to automatically focus on regions critical to the segmentation task by learning the correlation between multi-scale features. Adversarial learning, which explores the underlying relationship between labels in high-dimensional space, opens up a new way in 3D point cloud semantic segmentation. Experimental results on ScanNet and S3DIS datasets show that this framework effectively improves the segmentation quality and outperforms other state-of-the-art methods.© 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved....