Search engine for discovering works of Art, research articles, and books related to Art and Culture
ShareThis
Javascript must be enabled to continue!

Graph convolutional neural networks for 3D data analysis

View through CrossRef
(English) Deep Learning allows the extraction of complex features directly from raw input data, eliminating the need for hand-crafted features from the classical Machine Learning pipeline. This new paradigm brought a boost in the performance across several domains, including computer vision, natural language processing and audio processing. However, there are still challenges when dealing with unorganized structures. This thesis addresses this challenge using Graph Convolutional Neural Networks, a new set of techniques capable of managing graph structures that can be used for processing 3D data. The first part of the thesis focuses on the Graph Analysis task, in which we will study the capabilities of Graph Convolutional Neural Networks to capture the intrinsic geometric information of 3D data. We propose the Attention Graph Convolution layer that learns to infer the kernel used during the convolution, taking into account the particularities of each neighbourhood of the graph. We explore two variants of the Attention Graph Convolution layer, one that explores a residual approach and another one that allows the convolution to combine different neighbourhood domains. Furthermore, we propose a set of 3D pooling layers that mimics the behaviour of the pooling layers found in common 2D Convolutional Neural Networks architectures. Finally, we present a 2D-3D Fusion block capable of merging the 3D geometric information that we get from a Graph Convolutional Neural Network with the texture information obtained by a 2D Convolutional Neural Network. We evaluate the presented contributions on the RGB-D Scene Classification task. The second part of this thesis focuses on the Node Analysis task, which consists of extracting features on a node level, taking into account the neighbourhood structure. We present the Multi-Aggregator Graph Convolution layer that uses a multiple aggregator approach to better generalize for unseen topologies and learn better local representations. In addition, it reduces the memory footprint with respect to the Attention Graph Convolution layer. Finally, we analyze the capabilities of our proposed Graph Convolution layers to deal with heterogeneous graphs where the nodes of the graph may belong to different modalities. We evaluate the presented contributions with the Computer Graphics process of skinning a character mesh. Specifically, we propose a Two-Stream Graph Neural Network capable of predicting the skinning weights of a 3D character. (Català) Deep Learning permet l'extracció de característiques complexes directament de les dades d'entrada, fet que elimina la necessitat d'escollir les característiques manualment que tenen les arquitectures clàssiques de Machine Learning. Aquest nou paradigma va portar una millora en el rendiment a diverses àrees com la visió artificial, el processament del llenguatge natural i el processament d'àudio. Tot i això, encara hi ha desafiaments quan es tracta de dades no estructurades. Aquesta tesi aborda aquests desafiaments utilitzant Graph Convolutional Neural Networks, un nou conjunt de tècniques capaces de tractar amb grafs que es poden fer servir per processar dades 3D. La primera part de la tesi se centra en la tasca d'anàlisi de grafs, on estudiarem les capacitats de les Graph Convolutional Neural Networks per capturar la informació geomètrica intrínseca de les dades 3D. Proposem l'Attention Graph Convolution que aprèn a inferir el filtre utilitzat durant la convolució, tenint en compte les particularitats de cada veïnatge del graf. Explorem dues variants de l'Attention Graph Convolution, una que explora un enfocament residual i una altra que permet que la convolució combini diferents dominis de veïnatge. A més, proposem un conjunt de capes d'agrupació 3D que imiten el comportament de les capes d'agrupació que es troben a les arquitectures clàssiques de 2D Convolutional Neural Networks. Finalment, presentem el 2D-3D Fusion block capaç de fusionar la informació geomètrica 3D que obtenim d'una Graph Convolutional Neural Network amb la informació de textura obtinguda per una 2D Convolutional Neural Network. Avaluem les contribucions presentades en la tasca de classificació d'escenes RGB-D. La segona part d'aquesta tesi se centra en la tasca d'anàlisi de nodes, que consisteix a extreure característiques a nivell de node, tenint en compte l'estructura del veïnatge. Presentem la Multi-Aggregator Graph Convolution que utilitza múltiples agregadors per generalitzar millor les topologies no vistes i aprendre millors representacions locals. A més, redueix la memòria necessària en comparació a l'Attention Graph Convolution. Finalment, analitzem les capacitats de les nostres Graph Convolution proposades per tractar amb grafs heterogenis on els nodes del graf poden contenir diferents modalitats. Avaluem les contribucions presentades amb el procés, que pertany a la disciplina de Computer Graphics, per calcular les contribucions d'un esquelet 3D a la deformació d'un mesh. Específicament, proposem una Two-Stream Graph Neural Network capaç de predir els valors de les contribucions d'un esquelet 3D a la deformació d'un mesh.
Universitat Politècnica de Catalunya
Title: Graph convolutional neural networks for 3D data analysis
Description:
(English) Deep Learning allows the extraction of complex features directly from raw input data, eliminating the need for hand-crafted features from the classical Machine Learning pipeline.
This new paradigm brought a boost in the performance across several domains, including computer vision, natural language processing and audio processing.
However, there are still challenges when dealing with unorganized structures.
This thesis addresses this challenge using Graph Convolutional Neural Networks, a new set of techniques capable of managing graph structures that can be used for processing 3D data.
The first part of the thesis focuses on the Graph Analysis task, in which we will study the capabilities of Graph Convolutional Neural Networks to capture the intrinsic geometric information of 3D data.
We propose the Attention Graph Convolution layer that learns to infer the kernel used during the convolution, taking into account the particularities of each neighbourhood of the graph.
We explore two variants of the Attention Graph Convolution layer, one that explores a residual approach and another one that allows the convolution to combine different neighbourhood domains.
Furthermore, we propose a set of 3D pooling layers that mimics the behaviour of the pooling layers found in common 2D Convolutional Neural Networks architectures.
Finally, we present a 2D-3D Fusion block capable of merging the 3D geometric information that we get from a Graph Convolutional Neural Network with the texture information obtained by a 2D Convolutional Neural Network.
We evaluate the presented contributions on the RGB-D Scene Classification task.
The second part of this thesis focuses on the Node Analysis task, which consists of extracting features on a node level, taking into account the neighbourhood structure.
We present the Multi-Aggregator Graph Convolution layer that uses a multiple aggregator approach to better generalize for unseen topologies and learn better local representations.
In addition, it reduces the memory footprint with respect to the Attention Graph Convolution layer.
Finally, we analyze the capabilities of our proposed Graph Convolution layers to deal with heterogeneous graphs where the nodes of the graph may belong to different modalities.
We evaluate the presented contributions with the Computer Graphics process of skinning a character mesh.
Specifically, we propose a Two-Stream Graph Neural Network capable of predicting the skinning weights of a 3D character.
(Català) Deep Learning permet l'extracció de característiques complexes directament de les dades d'entrada, fet que elimina la necessitat d'escollir les característiques manualment que tenen les arquitectures clàssiques de Machine Learning.
Aquest nou paradigma va portar una millora en el rendiment a diverses àrees com la visió artificial, el processament del llenguatge natural i el processament d'àudio.
Tot i això, encara hi ha desafiaments quan es tracta de dades no estructurades.
Aquesta tesi aborda aquests desafiaments utilitzant Graph Convolutional Neural Networks, un nou conjunt de tècniques capaces de tractar amb grafs que es poden fer servir per processar dades 3D.
La primera part de la tesi se centra en la tasca d'anàlisi de grafs, on estudiarem les capacitats de les Graph Convolutional Neural Networks per capturar la informació geomètrica intrínseca de les dades 3D.
Proposem l'Attention Graph Convolution que aprèn a inferir el filtre utilitzat durant la convolució, tenint en compte les particularitats de cada veïnatge del graf.
Explorem dues variants de l'Attention Graph Convolution, una que explora un enfocament residual i una altra que permet que la convolució combini diferents dominis de veïnatge.
A més, proposem un conjunt de capes d'agrupació 3D que imiten el comportament de les capes d'agrupació que es troben a les arquitectures clàssiques de 2D Convolutional Neural Networks.
Finalment, presentem el 2D-3D Fusion block capaç de fusionar la informació geomètrica 3D que obtenim d'una Graph Convolutional Neural Network amb la informació de textura obtinguda per una 2D Convolutional Neural Network.
Avaluem les contribucions presentades en la tasca de classificació d'escenes RGB-D.
La segona part d'aquesta tesi se centra en la tasca d'anàlisi de nodes, que consisteix a extreure característiques a nivell de node, tenint en compte l'estructura del veïnatge.
Presentem la Multi-Aggregator Graph Convolution que utilitza múltiples agregadors per generalitzar millor les topologies no vistes i aprendre millors representacions locals.
A més, redueix la memòria necessària en comparació a l'Attention Graph Convolution.
Finalment, analitzem les capacitats de les nostres Graph Convolution proposades per tractar amb grafs heterogenis on els nodes del graf poden contenir diferents modalitats.
Avaluem les contribucions presentades amb el procés, que pertany a la disciplina de Computer Graphics, per calcular les contribucions d'un esquelet 3D a la deformació d'un mesh.
Específicament, proposem una Two-Stream Graph Neural Network capaç de predir els valors de les contribucions d'un esquelet 3D a la deformació d'un mesh.

Related Results

CG-TGAN: Conditional Generative Adversarial Networks with Graph Neural Networks for Tabular Data Synthesizing
CG-TGAN: Conditional Generative Adversarial Networks with Graph Neural Networks for Tabular Data Synthesizing
Data sharing is necessary for AI to be widely used, but sharing sensitive data with others with privacy is risky. To solve these problems, it is necessary to synthesize realistic t...
Fuzzy Chaotic Neural Networks
Fuzzy Chaotic Neural Networks
An understanding of the human brain’s local function has improved in recent years. But the cognition of human brain’s working process as a whole is still obscure. Both fuzzy logic ...
Bootstrapping a Biodiversity Knowledge Graph
Bootstrapping a Biodiversity Knowledge Graph
The "biodiversity knowledge graph" is a nice metaphor for connecting biodiversity data sources, but can we actually build it? Do we have sufficient linked data available? Given tha...
On the role of network dynamics for information processing in artificial and biological neural networks
On the role of network dynamics for information processing in artificial and biological neural networks
Understanding how interactions in complex systems give rise to various collective behaviours has been of interest for researchers across a wide range of fields. However, despite ma...
Data Analytics on Graphs Part I: Graphs and Spectra on Graphs
Data Analytics on Graphs Part I: Graphs and Spectra on Graphs
The area of Data Analytics on graphs promises a paradigm shift, as we approach information processing of new classes of data which are typically acquired on irregular but structure...
Abstract 902: Explainable AI: Graph machine learning for response prediction and biomarker discovery
Abstract 902: Explainable AI: Graph machine learning for response prediction and biomarker discovery
Abstract Accurately predicting drug sensitivity and understanding what is driving it are major challenges in drug discovery. Graphs are a natural framework for captu...
Using local convolutional neural networks for genomic prediction
Using local convolutional neural networks for genomic prediction
ABSTRACT The prediction of breeding values and phenotypes is of central importance for both livestock and crop breeding. With increasing computational power and mor...

Back to Top