Superpixel Image Classification with Graph Attention Networks

Avelar, Pedro H. C.; Tavares, Anderson R.; Silveira, Thiago L. T. da; Jung, Cláudio Rosito; Lamb, Luís C.

doi:10.1109/sibgrapi51738.2020.00035

Cited by 41 publications

(16 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Acc. (max) MoNet [43] 91.11 SplineCNN [14] 95.22 GCGP [59] 95.80 GAT [4] 96.19 PNCNN [15] 98.76 PolyConv (squeezed) 98.39 PolyConv (unsqueezed) 98.95…”

Section: Methodsmentioning

confidence: 99%

PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation

Yavartanoo¹,

Hung²,

Neshatavar³

et al. 2021

Preprint

View full text Add to dashboard Cite

3D shape representation and its processing have substantial effects on 3D shape recognition. The polygon mesh as a 3D shape representation has many advantages in computer graphics and geometry processing. However, there are still some challenges for the existing deep neural network (DNN)-based methods on polygon mesh representation, such as handling the variations in the degree and permutations of the vertices and their pairwise distances. To overcome these challenges, we propose a DNNbased method (PolyNet) and a specific polygon mesh representation (PolyShape) with a multi-resolution structure. PolyNet contains two operations; (1) a polynomial convolution (PolyConv) operation with learnable coefficients, which learns continuous distributions as the convolutional filters to share the weights across different vertices, and (2) a polygonal pooling (PolyPool) procedure by utilizing the multi-resolution structure of PolyShape to aggregate the features in a much lower dimension. Our experiments demonstrate the strength and the advantages of PolyNet on both 3D shape classification and retrieval tasks compared to existing polygon mesh-based methods and its superiority in classifying graph representations of images. The code is publicly available from this link.

show abstract

“…Acc. (max) MoNet [43] 91.11 SplineCNN [14] 95.22 GCGP [59] 95.80 GAT [4] 96.19 PNCNN [15] 98.76 PolyConv (squeezed) 98.39 PolyConv (unsqueezed) 98.95…”

Section: Methodsmentioning

confidence: 99%

PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation

Yavartanoo¹,

Hung²,

Neshatavar³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…With the vigorous development of GNN models, their applications have become more and more extensive in various fields, such as social networks [41], recommendation systems [42], life sciences [43], and so on. For unstructured data such as images, superpixels can transform images into graph structures, thus solving image-related tasks using graph neural networks [44][45][46]. Note that the application of GNNs in the field of computer vision, where semantic segmentation is an important task, has attracted more and more attention.…”

Section: Graph Neural Networkmentioning

confidence: 99%

Superpixel-Based Attention Graph Neural Network for Semantic Segmentation in Aerial Images

Diao

Zhang

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Semantic segmentation is one of the significant tasks in understanding aerial images with high spatial resolution. Recently, Graph Neural Network (GNN) and attention mechanism have achieved excellent performance in semantic segmentation tasks in general images and been applied to aerial images. In this paper, we propose a novel Superpixel-based Attention Graph Neural Network (SAGNN) for semantic segmentation of high spatial resolution aerial images. A K-Nearest Neighbor (KNN) graph is constructed from our network for each image, where each node corresponds to a superpixel in the image and is associated with a hidden representation vector. On this basis, the initialization of the hidden representation vector is the appearance feature extracted by a unary Convolutional Neural Network (CNN) from the image. Moreover, relying on the attention mechanism and recursive functions, each node can update its hidden representation according to the current state and the incoming information from its neighbors. The final representation of each node is used to predict the semantic class of each superpixel. The attention mechanism enables graph nodes to differentially aggregate neighbor information, which can extract higher-quality features. Furthermore, the superpixels not only save computational resources, but also maintain object boundary to achieve more accurate predictions. The accuracy of our model on the Potsdam and Vaihingen public datasets exceeds all benchmark approaches, reaching 90.23% and 89.32%, respectively.

show abstract

“…Relational GCNs [41] add to this framework by also considering multiple edge types, namely, relations (such as temporal and spatial relations), and the aggregating information from each relation via separate weights in a single layer. Recently, GCNs have been adopted for tasks involving audio [12,61] and images [33,11,5]. Following the success of graph models to efficiently perform image-based tasks, we are eager to demonstrate our extension of the image-graph representation to videos.…”

Section: Graph Convolutional Neural Networkmentioning

confidence: 99%

“…One can clearly discern a person playing a guitar in both images. A different way of depicting the relations between superpixels is a graph with nodes representing superpixels [33,11,5]. Such a representation has the advantage of being invariant to rotations and flips, which obviates the need for further augmentations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GraphVid: It Only Takes a Few Nodes to Understand a Video

Kosman¹,

Castro²

2022

Preprint

View full text Add to dashboard Cite

We propose a concise representation of videos that encode perceptually meaningful features into graphs. With this representation, we aim to leverage the large amount of redundancies in videos and save computations. First, we construct superpixel-based graph representations of videos by considering superpixels as graph nodes and create spatial and temporal connections between adjacent superpixels. Then, we leverage Graph Convolutional Networks to process this representation and predict the desired output. As a result, we are able to train models with much fewer parameters, which translates into short training periods and a reduction in computation resource requirements. A comprehensive experimental study on the publicly available datasets Kinetics-400 and Charades shows that the proposed method is highly cost-effective and uses limited commodity hardware during training and inference. It reduces the computational requirements 10-fold while achieving results that are comparable to state-ofthe-art methods. We believe that the proposed approach is a promising direction that could open the door to solving video understanding more efficiently and enable more resource limited users to thrive in this research field.

show abstract

Superpixel Image Classification with Graph Attention Networks

Cited by 41 publications

References 19 publications

PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation

PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation

Superpixel-Based Attention Graph Neural Network for Semantic Segmentation in Aerial Images

GraphVid: It Only Takes a Few Nodes to Understand a Video

Contact Info

Product

Resources

About