PIG-Net: Inception based deep learning architecture for 3D point cloud segmentation

Hegde, Sindhu B; Gangisetty, Shankar

doi:10.1016/j.cag.2021.01.004

Cited by 29 publications

(17 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent studies highlight that the efficiency of 3D point cloud segmentation models is a serious concern for the community [18,20,6]. However, the majority of new and advanced deep learning models emphasize on the improvement of segmentation accuracy, providing almost no information on the models' efficiency [8,10,13,14].…”

Section: Related Workmentioning

confidence: 99%

Effective Early Stopping of Point Cloud Neural Networks

Zoumpekas

Salamó

Puig

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Early stopping techniques can be utilized to decrease the time cost, however currently the ultimate goal of early stopping techniques is closely related to the accuracy upgrade or the ability of the neural network to generalize better on unseen data without being large or complex in structure and not directly with its efficiency. Time efficiency is a critical factor in neural networks, especially when dealing with the segmentation of 3D point cloud data, not only because a neural network itself is computationally expensive, but also because point clouds are large and noisy data, making learning processes even more costly. In this paper, we propose a new early stopping technique based on fundamental mathematics aiming to upgrade the trade-off between the learning efficiency and accuracy of neural networks dealing with 3D point clouds. Our results show that by employing our early stopping technique in four distinct and highly utilized neural networks in segmenting 3D point clouds, the training time efficiency of the models is greatly improved, with efficiency gain values reaching up to 94%, while the models achieving in just a few epochs approximately similar segmentation accuracy metric values like the ones that are obtained in the training of the neural networks in 200 epochs. Also, our proposal outperforms four conventional early stopping approaches in segmentation accuracy, implying a promising innovative early stopping technique in point cloud segmentation.

show abstract

Section: Related Workmentioning

confidence: 99%

Effective Early Stopping of Point Cloud Neural Networks

Zoumpekas

Salamó

Puig

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…In computer graphics, intensive researches have been done to extract the functionally meaningful regions through semantic segmentation. Convolutional neural network and fully convolutional network have shown a well‐done result in this deep problem (Hegde & Gangisetty, 2021; Wen et al., 2020).…”

Section: Reverse Modelingmentioning

confidence: 99%

Automated inspection and monitoring of member deformation in grid structures

Wei

Fan

Liu

et al. 2021

Computer aided Civil Eng

View full text Add to dashboard Cite

In large-span grid structures with thousands of members involved, bending deformation of members is one of the most commonly observed damages affecting the normal service, even the safety of structures. Traditional testing and monitoring methods show weakness in the accurate judgment of crooked members and precision of deformation measurements. In this paper, a new deformation inspection and monitoring method of grid structures using image-based 3D reconstruction is proposed, wherein a new method is put forward to automatically recognize and extract the shape deformation of the structural member for the first time. First, the key area with multiple members is modeled as a threedimensional mesh model using image-based 3D reconstruction. Then, a new automated recognition and extraction algorithm of shape deformation (AREAS) is carried out, and crooked members, together with their deformed shapes, are extracted from the mesh model through AREAS. In this study, a load experiment of a quadrangular pyramid grid structure containing artificial crooked members and speckled members is designed to compare the deformation measurements using image-based 3D reconstruction with those using laser scanning. The comparison of deformation and deformation increment shows an average error within 1 mm for image-based 3D reconstruction, which validates the proposed method in on-site inspection and monitoring.

show abstract

“…The l 2 -norm pooling (L2P), average pooling (AP) [14], and max pooling (MP) [15] produce the l 2 -norm, average, and maximum values within the block B m 1 ,m 2 , respectively. Their formula can be written as below:…”

Section: Stochastic Poolingmentioning

confidence: 99%

SOSPCNN: Structurally Optimized Stochastic Pooling Convolutional Neural Network for Tetralogy of Fallot Recognition

Wang

Chu³

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Aim. This study proposes a new artificial intelligence model based on cardiovascular computed tomography for more efficient and precise recognition of Tetralogy of Fallot (TOF). Methods. Our model is a structurally optimized stochastic pooling convolutional neural network (SOSPCNN), which combines stochastic pooling, structural optimization, and convolutional neural network. In addition, multiple-way data augmentation is used to overcome overfitting. Grad-CAM is employed to provide explainability to the proposed SOSPCNN model. Meanwhile, both desktop and web apps are developed based on this SOSPCNN model. Results. The results on ten runs of 10-fold crossvalidation show that our SOSPCNN model yields a sensitivity of 92.25 ± 2.19 , a specificity of 92.75 ± 2.49 , a precision of 92.79 ± 2.29 , an accuracy of 92.50 ± 1.18 , an F1 score of 92.48 ± 1.17 , an MCC of 85.06 ± 2.38 , an FMI of 92.50 ± 1.17 , and an AUC of 0.9587. Conclusion. The SOSPCNN method performed better than three state-of-the-art TOF recognition approaches.

show abstract

PIG-Net: Inception based deep learning architecture for 3D point cloud segmentation

Cited by 29 publications

References 29 publications

Effective Early Stopping of Point Cloud Neural Networks

Effective Early Stopping of Point Cloud Neural Networks

Automated inspection and monitoring of member deformation in grid structures

SOSPCNN: Structurally Optimized Stochastic Pooling Convolutional Neural Network for Tetralogy of Fallot Recognition

Contact Info

Product

Resources

About