.png){kind=icon}
返回
Joint object contour points and semantics for instance segmentation
.png){kind=icon}
OA
AI
DOI：10.1111/exsy.13504.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The edges of objects are of great significance to the task of instance segmentation. However, most of the current popular deep neural networks do not pay much attention to the object edge information. More importantly, using the down-sampling pooling layer in the deep learning network, the edge detail information of the object will be lost. To address this issue, inspired by the manual annotation process, we propose Mask Point R-CNN aiming at promoting the neural network's attention to the object boundary. Specifically, we introduce the auxiliary task of object contour point detection on the Mask R-CNN framework, which can effectively improve the gradient flow between different tasks by multi-task learning and repairing objects' boundary information via feature fusion. Consequently, the model can be more sensitive to the edges of the object and capture more geometric features. Quantitatively, the experimental results show that our Mask Point R-CNN outperforms vanilla Mask R-CNN by 3.8% on the Cityscapes dataset and 0.8% on the COCO dataset.
Keyword:
feature fusion
instance segmentation
multi-task learning
object boundary
期刊
IF:
2.3
论文数:
2.5K
被引数:
3.8K
机构
引用论文
分享收藏Excellent microwave absorption of Y2Fe15.5Co0.5Si/paraffin composites by tuning powder particle size
PREAI
分享收藏分享收藏Attention Mask R-CNN for Ship Detection and Segmentation From Remote Sensing Images.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容