ADM-Net: attentional-deconvolution module-based net for noise-coupled traffic sign recognition

Chung, Jun Ho; Kim, Dong Won; Kang, Tae-Koo; Lim, Myo Taeg

doi:10.1007/s11042-022-12219-1

Cited by 3 publications

(3 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, using this method for recognition in harsh environments requires large memory relatively. Chung proposed an attentional deconvolution module (ADM) based network (ADM-Net) [ 33 ]. The network uses ADM, convolutional pools and full convolutional networks to improve classification under such harsh conditions.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A lightweight network for traffic sign recognition based on multi-scale feature and attention mechanism

Wei,

Zhang,

Yang

et al. 2024

Heliyon

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

“…For example, they are sensitive to environmental factors such as light, noise and so on [ 2 ]. Besides, different kinds of traffic signs need different feature extractors [ 3 , 4 ]. Deep neural networks (DNN) have achieved great success in the field of image recognition with the development of deep learning technology.…”

Section: Introductionmentioning

confidence: 99%

A lightweight network for traffic sign recognition based on multi-scale feature and attention mechanism

Wei,

Zhang,

Yang

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…Currently, the receptive field size for a large object is not sufficient for traffic signs because traffic signs are much smaller than other objects. Finally, we adopt the ADM-Net [44] as a classifier in the detection algorithm. The ADM-Net comprises the attentional-deconvolution module (ADM) within the network to maximize the feature information with the attention mechanism.…”

Section: Introductionmentioning

confidence: 99%

Feature-Selection-Based Attentional-Deconvolution Detector for German Traffic Sign Detection Benchmark

et al. 2023

Self Cite

View full text Add to dashboard Cite

In this study, we propose a novel traffic sign detection algorithm based on the deeplearning approach. The proposed algorithm, which we termed the feature-selection-based attentionaldeconvolution detector (FSADD), is used along with the “you look only once” (YOLO) v5 structure for feature selection. When applying feature selection inside a detection algorithm, the network divides the extracted feature maps after the convolution layer into similar and non similar feature maps. Generally, the feature maps obtained after the convolution layers are the outputs of filters with random weights. Owing to the randomness of the filter, the network obtains various kinds of feature maps with unnecessary components, which degrades the detection performance. However, grouping feature maps with high similarities can increase the relativeness of each feature map, thereby improving the network detection of specific targets from images. Furthermore, the proposed FSADD model has modified sizes of the receptive fields for improved traffic sign detection performance. Many of the available general detection algorithms are unsuitable for the German traffic sign detection benchmark (GTSDB) because of the small sizes of these signs in the images. Experimental comparisons were performed with respect to the GTSDB to show that the proposed FSADD is comparable to the state-of-the-art while detecting 29 kinds of traffic signs with 73.9% accuracy of classification performances.

show abstract

TSD-DETR: A lightweight real-time detection transformer of traffic sign detection for long-range perception of autonomous driving

Zhang,

Yang,

Han

et al. 2025

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

ADM-Net: attentional-deconvolution module-based net for noise-coupled traffic sign recognition

Cited by 3 publications

References 61 publications

A lightweight network for traffic sign recognition based on multi-scale feature and attention mechanism

A lightweight network for traffic sign recognition based on multi-scale feature and attention mechanism

Feature-Selection-Based Attentional-Deconvolution Detector for German Traffic Sign Detection Benchmark

TSD-DETR: A lightweight real-time detection transformer of traffic sign detection for long-range perception of autonomous driving

Contact Info

Product

Resources

About