Grammar Guided Genetic Programming for Network Architecture Search and Road Detection on Aerial Orthophotography

Castillo, Víctor de la Fuente; Díaz-Álvarez, Alberto; Callejo, Miguel Ángel Manso; Serradilla, Francisco

doi:10.3390/app10113953

Cited by 7 publications

(7 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the advent of AlexNet [16], there has been tremendous growth in the research and performance of Deep neural networks. There have been numerous experiments and much research conducted with different computer vision models such as VGNet [17], Resnet [18], InceptionNet [19], etc. The documents are treated as conventional images and thus have the models delivered satisfactory results with classification tasks.…”

Section: Introductionmentioning

confidence: 99%

EmmDocClassifier: Efficient Multimodal Document Image Classifier for Scarce Data

et al. 2022

View full text Add to dashboard Cite

Document classification is one of the most critical steps in the document analysis pipeline. There are two types of approaches for document classification, known as image-based and multimodal approaches. Image-based document classification approaches are solely based on the inherent visual cues of the document images. In contrast, the multimodal approach co-learns the visual and textual features, and it has proved to be more effective. Nonetheless, these approaches require a huge amount of data. This paper presents a novel approach for document classification that works with a small amount of data and outperforms other approaches. The proposed approach incorporates a hierarchical attention network (HAN) for the textual stream and the EfficientNet-B0 for the image stream. The hierarchical attention network in the textual stream uses dynamic word embedding through fine-tuned BERT. HAN incorporates both the word level and sentence level features. While earlier approaches rely on training on a large corpus (RVL-CDIP), we show that our approach works with a small amount of data (Tobacco-3482). To this end, we trained the neural network at Tobacco-3482 from scratch. Therefore, we outperform the state-of-the-art by obtaining an accuracy of 90.3%. This results in a relative error reduction rate of 7.9%.

show abstract

Section: Introductionmentioning

confidence: 99%

EmmDocClassifier: Efficient Multimodal Document Image Classifier for Scarce Data

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The second was the design of convolutional modules, e.g., the annealing module used in Squeeze Net to achieve light-weighting by reducing the network parameters [ 71 , 72 ]. The third was to use searching mechanisms in the network architecture to disconnect invalid neurons and retain the valid connections alone [ 73 , 74 , 75 ]. All of the above solutions had some drawbacks in this study.…”

Section: Methodsmentioning

confidence: 99%

Table Tennis Track Detection Based on Temporal Feature Multiplexing Network

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

Recording the trajectory of table tennis balls in real-time enables the analysis of the opponent’s attacking characteristics and weaknesses. The current analysis of the ball paths mainly relied on human viewing, which lacked certain theoretical data support. In order to solve the problem of the lack of objective data analysis in the research of table tennis competition, a target detection algorithm-based table tennis trajectory extraction network was proposed to record the trajectory of the table tennis movement in video. The network improved the feature reuse rate in order to achieve a lightweight network and enhance the detection accuracy. The core of the network was the “feature store & return” module, which could store the output of the current network layer and pass the features to the input of the network layer at the next moment to achieve efficient reuse of the features. In this module, the Transformer model was used to secondarily process the features, build the global association information, and enhance the feature richness of the feature map. According to the designed experiments, the detection accuracy of the network was 96.8% for table tennis and 89.1% for target localization. Moreover, the parameter size of the model was only 7.68 MB, and the detection frame rate could reach 634.19 FPS using the hardware for the tests. In summary, the network designed in this paper has the characteristics of both lightweight and high precision in table tennis detection, and the performance of the proposed model significantly outperforms that of the existing models.

show abstract

“…The goal is to learn underlying hidden distribution of the data using just the unlabeled data. In [16], unsupervised learning based on grammar-guided genetic programming has been successfully applied to obtain new Convolutional Neural Network (CNN) architectures specialized in road recognition in aerial imagery. In [17], unsupervised training was applied to generate filters that improved the predictions of the road detection model.…”

Section: Related Workmentioning

confidence: 99%

Generative Learning for Postprocessing Semantic Segmentation Predictions: A Lightweight Conditional Generative Adversarial Network Based on Pix2pix to Improve the Extraction of Road Surface Areas

Cira

Callejo

Alcarria

et al. 2021

Land

Self Cite

View full text Add to dashboard Cite

Remote sensing experts have been actively using deep neural networks to solve extraction tasks in high-resolution aerial imagery by means of supervised semantic segmentation operations. However, the extraction operation is imperfect, due to the complex nature of geospatial objects, limitations of sensing resolution, or occlusions present in the scenes. In this work, we tackle the challenge of postprocessing semantic segmentation predictions of road surface areas obtained with a state-of-the-art segmentation model and present a technique based on generative learning and image-to-image translations concepts to improve these initial segmentation predictions. The proposed model is a conditional Generative Adversarial Network based on Pix2pix, heavily modified for computational efficiency (92.4% decrease in the number of parameters in the generator network and 61.3% decrease in the discriminator network). The model is trained to learn the distribution of the road network present in official cartography, using a novel dataset containing 6784 tiles of 256 × 256 pixels in size, covering representative areas of Spain. Afterwards, we conduct a metrical comparison using the Intersection over Union (IoU) score (measuring the ratio between the overlap and union areas) on a novel testing set containing 1696 tiles (unseen during training) and observe a maximum increase of 11.6% in the IoU score (from 0.6726 to 0.7515). In the end, we conduct a qualitative comparison to visually assess the effectiveness of the technique and observe great improvements with respect to the initial semantic segmentation predictions.

show abstract

Grammar Guided Genetic Programming for Network Architecture Search and Road Detection on Aerial Orthophotography

Cited by 7 publications

References 64 publications

EmmDocClassifier: Efficient Multimodal Document Image Classifier for Scarce Data

EmmDocClassifier: Efficient Multimodal Document Image Classifier for Scarce Data

Table Tennis Track Detection Based on Temporal Feature Multiplexing Network

Generative Learning for Postprocessing Semantic Segmentation Predictions: A Lightweight Conditional Generative Adversarial Network Based on Pix2pix to Improve the Extraction of Road Surface Areas

Contact Info

Product

Resources

About