.png){kind=icon}
返回
Improving CNN-based semantic segmentation on structurally similar data using contrastive graph convolutional networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.110622.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Structurally similar data exist in most practical semantic segmentation applications. For example, objects can appear identical or positionally similar in many images, such as video frames. Objects with structural similarity in data samples can confuse deep neural networks (DNNs) in semantic segmentation applications. These challenges often lead to lower pixel classification accuracy of natural object segmentation. This study proposes a novel approach (S2-GCN) that enhances CNN -based semantic segmentation for structurally similar data using a contrastive graph convolutional network (GCN). By selecting specific label pairs and developing a customized GCN branch parallel to an encoder -decoder backbone, our method significantly improves accuracy, IoU, and F1score, by up to 8 %, as demonstrated through an extensive evaluation of five datasets. Our findings show that the proposed method effectively addresses the structural similarity problem of CNN -based semantic segmentation and can be applied to a wide range of practical applications.
Keyword:
Semantic segmentation
Structural similarity
Graph network
Contrastive learning
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
A multi-strategy contrastive learning framework for weakly supervised semantic segmentation一种用于弱监督语义分割的多策略对比学习框架.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏O-SegNet: Robust Encoder and Decoder Architecture for Objects Segmentation From Aerial Imagery Data
PREAI
分享收藏
Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THVRSC Advances
RSC AdvancesIF0
PREAI
分享收藏Learning pseudo labels for semi-and-weakly supervised semantic segmentation用于半监督和弱监督语义分割的学习伪标签PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏A deep neural network based correction scheme for improved air-tissue boundary prediction in real-time magnetic resonance imaging video一种基于深度神经网络的实时磁共振成像视频空气组织边界预测校正方法
PREAI
分享收藏Deep clustering for weakly-supervised semantic segmentation in autonomous driving scenesNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容