HierarchyNet: Hierarchical CNN-Based Urban Building Classification

Taoufiq, Salma; Nagy, Balázs; Benedek, Csaba

doi:10.3390/rs12223794

Cited by 30 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The addition of new feature maps is realized according to the principle presented in section III. The level 2 networks of our grafting approach thus take as input arrays of size (56,56,24).…”

Section: Cifar-10 Resultsmentioning

confidence: 99%

“…HierarchyNet [24] has recently been proposed as an improvement over the B-CNN, in particular, by reducing the number of added parameters. Through their approach, the authors also make predictions at different levels.…”

Section: Related Workmentioning

confidence: 99%

“…Unlike the pruning solutions, we remove here several layers from the second model and keep the other layers unchanged so that we can specialize each second model for a distinct classification subproblem. Although we can make a link with B-CNN [21] and HierarchyNet [24] in which we add branches, differences remain. For example, we want to be able to decide not to compute a branch if the coarse prediction is sufficiently informative.…”

Section: Proposed Approachmentioning

confidence: 99%

See 2 more Smart Citations

Grafting Heterogeneous Neural Networks for a Hierarchical Object Classification

et al. 2022

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) are deep learning architectures used for image classification that have been improved in recent years to increase their accuracies and reduce their computation times. Hierarchical approaches are based on a step-by-step strategy and aim to optimize performance on difficult tasks by solving successive subtasks. The gain provided by these solutions must be relativized with the explosion in the number of parameters they imply, which makes their implementation on embedded systems difficult. New constraints also appear in the choice of the architectures of the branches when one seeks to have a global network providing predictions at different levels. We propose a strategy that allows the merging of heterogeneous CNNs by following a hierarchical approach in which the information extracted by first-level networks can be fed back at any location into second-level networks. Despite the differences in the number and size of the feature maps, such grafting can be done by using clustering, dimension reduction, and interpolation techniques. This strategy eliminates the computational redundancy induced by the recalculation of low-level features. The proposed grafting approach significantly reduces the inference time of the second network without impacting the accuracy. Tests performed on MNIST, CIFAR-10, and PlantVillage datasets with several CNNs illustrate the possibility of implementation in various situations. Our solution allows us to consider in an innovative way the implementation of hierarchical solutions on devices with limited capacities.

show abstract

Section: Cifar-10 Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Proposed Approachmentioning

confidence: 99%

See 1 more Smart Citation

Grafting Heterogeneous Neural Networks for a Hierarchical Object Classification

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In this paper, we address the research problem of windows instance segmentation from frontal facade images (see Figure 1). The accurate extraction of windows is challenging owing to the complexity of buildings in real scenes [5,6]. Specifically, the diversity of building styles usually results in a variety of window geometries.…”

Section: Introductionmentioning

confidence: 99%

DeepWindows: Windows Instance Segmentation through an Improved Mask R-CNN Using Spatial Attention and Relation Modules

Sun

Malihi

et al. 2022

IJGI

View full text Add to dashboard Cite

Windows, as key components of building facades, have received increasing attention in facade parsing. Convolutional neural networks have shown promising results in window extraction. Most existing methods segment a facade into semantic categories and subsequently employ regularization based on the structure of manmade architectures. These methods merely concern the optimization of individual windows, without considering the spatial areas or relationships of windows. This paper presents a novel windows instance segmentation method based on Mask R-CNN architecture. The method features a spatial attention region proposal network and a relation module-enhanced head network. First, an attention module is introduced in the region proposal network to generate a spatial attention map, then the attention map is multiplied with the objectness scores of the classification branch. Second, for the head network, relation modules are added to model the spatial relationships between proposals. Appearance and geometric features are combined for instance recognition. Furthermore, we constructed a new window instance segmentation dataset with 1200 annotated images. With our dataset, the average precisions of our method on detection and segmentation increased from 53.1% and 53.7% to 56.4% and 56.7% compared with Mask R-CNN. A comparison with state-of-the-art methods also proves the predominance of our proposed method.

show abstract

“…The selection of the most suitable CNN architecture depends on the task to be performed. For example, some of them such as GoogleNet, ResNetm, VGG or AlexNet are remarkable according to their excellent results in classification [14,[19][20][21].…”

Section: Introductionmentioning

confidence: 99%

A CNN Regression Approach to Mobile Robot Localization Using Omnidirectional Images

et al. 2021

View full text Add to dashboard Cite

Understanding the environment is an essential ability for robots to be autonomous. In this sense, Convolutional Neural Networks (CNNs) can provide holistic descriptors of a scene. These descriptors have proved to be robust in dynamic environments. The aim of this paper is to perform hierarchical localization of a mobile robot in an indoor environment by means of a CNN. Omnidirectional images are used as the input of the CNN. Experiments include a classification study in which the CNN is trained so that the robot is able to find out the room where it is located. Additionally, a transfer learning technique transforms the original CNN into a regression CNN which is able to estimate the coordinates of the position of the robot in a specific room. Regarding classification, the room retrieval task is performed with considerable success. As for the regression stage, when it is performed along with an approach based on splitting rooms, it also provides relatively accurate results.

show abstract

HierarchyNet: Hierarchical CNN-Based Urban Building Classification

Cited by 30 publications

References 28 publications

Grafting Heterogeneous Neural Networks for a Hierarchical Object Classification

Grafting Heterogeneous Neural Networks for a Hierarchical Object Classification

DeepWindows: Windows Instance Segmentation through an Improved Mask R-CNN Using Spatial Attention and Relation Modules

A CNN Regression Approach to Mobile Robot Localization Using Omnidirectional Images

Contact Info

Product

Resources

About