.png){kind=icon}
返回
Instance-level Context Attention Network for instance segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2021.11.104.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Instance segmentation has made great progress in recent years. However, current mainstream detection-based methods ignore the process of distinguishing different instances in the same detected region, mak-ing it hard to segment the correct instance when a detected region contains multiple instances. To address this problem, we propose an Instance-level Context Attention Network (ICANet) to generate more discrim-inative features for different instances based on the context from their respective instance scopes, called instance-level context. Specifically, given a detected region, we first propose an instance attention module to obtain the specific attention maps that focus on the relationships between pixel pairs from the same instance by learning an embedding space. With this type of attention map, the features from the same instance achieve mutual gains, while the features from different instances become more discriminative. Then, we propose a spatial attention module to incorporate spatial information and enhance feature rep-resentations based on both feature and spatial relations. Moreover, to obtain clearer attention maps, we further propose a weight clipping strategy to filter out the noise by cutting off the lower weight. We per -form extensive experiments to verify the effectiveness of the proposed method. As reported in the results, our method steadily outperforms the baseline by over 1.5% on the COCO dataset using different backbones and 3.7% on the Cityscapes dataset, which demonstrates the effectiveness of our method. (c) 2021 Elsevier B.V. All rights reserved.
Keyword:
Instance segmentation
Instance-level contextual information
Self-attention
Spatial information
Attention weight clipping
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
暂无机构信息
引用论文
分享收藏分享收藏Mask-MCNet: Tooth instance segmentation in 3D point clouds of intra-oral scansMasc-mcnet: 口腔内扫描的3D点云中的牙齿实例分割.png)
NEUROCOMPUTING
OAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏Single-shot weakly-supervised object detection guided by empirical saliency modelNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容