SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

Convolutional Neural Networks (CNNs) have been very successful at solving a variety of computer vision tasks such as object classification and detection, semantic segmentation, activity understanding, to name just a few. One key enabling factor for their great performance has been the ability to train very deep networks. Despite their huge success in many tasks, CNNs do not work well with non-Euclidean data, which is prevalent in many real-world applications. Graph Convolutional Networks (GCNs) offer an alternative that allows for non-Eucledian data input to a neural network. While GCNs already achieve encouraging results, they are currently limited to architectures with a relatively small number of layers, primarily due to vanishing gradients during training. This work transfers concepts such as residual/dense connections and dilated convolutions from CNNs to GCNs in order to successfully train very deep GCNs. We show the benefit of using deep GCNs (with as many as 112 layers) experimentally across various datasets and tasks. Specifically, we achieve very promising performance in part segmentation and semantic segmentation on point clouds and in node classification of protein functions across biological protein-protein interaction (PPI) graphs. We believe that the insights in this work will open avenues for future research on GCNs and their application to further tasks not explored in this paper.

show abstract

“…These are lost in the results of PlainGCN-28. PointNet [33], PointNet++ [34], SpiderCNN [53] and PointCNN [54].…”

Section: Originalmentioning

confidence: 99%

DeepGCNs: Making GCNs Go as Deep as CNNs

Mueller

Qian

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

107

View full text Add to dashboard Cite

show abstract

“…Instead of uniform grids, hierarchical space partitioning structures (e.g., kd-trees, lattices) can be used to define regular convolutions [26,27,28,29,30]. Another type of networks incorporate point-wise convolution operators to directly process point clouds [31,32,33,34,35,36,37,38,39,40,41,42]. Alternatively, shapes can be treated as graphs by connecting each point to other points within neighborhoods in a feature space.…”

Section: Related Workmentioning

confidence: 99%

Cross-Shape Attention for Part Segmentation of 3D Point Clouds

Loizou¹,

Petrov²,

Averkiou³

et al. 2020

Preprint

View full text Add to dashboard Cite

We present a method that processes 3D point clouds by performing graph convolution operations across shapes. In this manner, point descriptors are learned by allowing interaction and propagation of feature representations within a shape collection. To enable this form of non-local, cross-shape graph convolution, our method learns a pairwise point attention mechanism indicating the degree of interaction between points on different shapes. Our method also learns to create a graph over shapes of an input collection whose edges connect shapes deemed as useful for performing cross-shape convolution. The edges are also equipped with learned weights indicating the compatibility of each shape pair for cross-shape convolution. Our experiments demonstrate that this interaction and propagation of point representations across shapes makes them more discriminative. In particular, our results show significantly improved performance for 3D point cloud semantic segmentation compared to conventional approaches, especially in cases with limited number of training examples.

show abstract

“…This simple approach yields a very general, well performing and robust algorithm, which has been reported by all three works. Since then, the MIL NN has been used in numerous applications, for example in causal reasoning [20], in computer vision to process point clouds [25,27], in medicine to predict prostate cancer [12], in training generative adversarial networks [12], or to process network traffic to detect infected computers [18]. The last work has demonstrated that the MIL NN construction can be nested (using sets of sets as an input), which allows the neural network to handle data with a hierarchical structure.…”

Section: Motivationmentioning

confidence: 99%

“…The paper only contains theoretical results -for experimental comparison to prior art, the reader is referred to [28,6,19,20,25,27,12,18]. However, the authors provide a proof of concept demonstration of processing JSON data at https://codeocean.com/capsule/182df525-8417-441f-80ef-4d3c02fea970/?ID=f4d3be809b144…”

Section: Motivationmentioning

confidence: 99%

Approximation capability of neural networks on spaces of probability measures and tree-structured domains

Pevny,

Kovarik

2019

Preprint

View full text Add to dashboard Cite

This paper extends the proof of density of neural networks in the space of continuous (or even measurable) functions on Euclidean spaces to functions on compact sets of probability measures. By doing so the work parallels a more then a decade old results on mean-map embedding of probability measures in reproducing kernel Hilbert spaces. The work has wide practical consequences for multi-instance learning, where it theoretically justifies some recently proposed constructions. The result is then extended to Cartesian products, yielding universal approximation theorem for tree-structured domains, which naturally occur in data-exchange formats like JSON, XML, YAML, AVRO, and ProtoBuffer. This has important practical implications, as it enables to automatically create an architecture of neural networks for processing structured data (AutoML paradigms), as demonstrated by an accompanied library for JSON format.

show abstract

SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

Cited by 21 publications

References 11 publications

DeepGCNs: Making GCNs Go as Deep as CNNs

DeepGCNs: Making GCNs Go as Deep as CNNs

Cross-Shape Attention for Part Segmentation of 3D Point Clouds

Approximation capability of neural networks on spaces of probability measures and tree-structured domains

Contact Info

Product

Resources

About