Abstract
Convolutional Neural Networks (CNNs) have become primary technologies in computer vision systems across multiple fields. Its central characteristic is to slide filters on input images and repeats the same procedures to obtain the image’s robust features. However, conventional CNNs struggle to classify objects when the input images are contaminated by unavoidable external noises such as missing information, blur, or illumination. This paper proposes an attentional-deconvolution module (ADM)-based net(ADM-Net) in which ADMs, convolutional-pooling, and a fully convolutional network (FCN) are applied to improve classification under such harsh conditions. The structure of ADM includes an attention layer, deconvolution layer and max-pooling. The attention layer and convolutional pooling help the proposed network maintain key features through convolution procedures under noise-coupled environments. The deconvolution layers and fully convolutional structure have advantages in providing additional information from upscale feature maps and enabling the network to store local pixel information. The ADM-Net was demonstrated on the German traffic sign recognition benchmark with different noise cases comparing densenet, multi-scale CNN, a committee of CNN, hierarchical CNN, and a multi-column deep neural network. Demonstrations of ADM-Net achieve the highest records in different cases such as 1) blur and missing information case: 86.637%, 2) missing information and illumination case: 92.329%, and 3) blur, missing information, and illumination case: 80.221%. Training datasets for ADM-Net have limited conditions, the proposed network demonstrates its robustness effectively under noise-coupled environments.
Similar content being viewed by others
Notes
Rectified Linear Unit
Convolution layer with zero-padding
References
Arcos-Garcia A, Alvarez-Garcia JA, Soria-Morillo LM (2012) Deep neural network for traffic sign recognition systems: an analysis of spatial transformers and stochastic optimisation methods. Neural Netw 99:158–165
Bangquan X, Xiong WX (2019) Real-time embedded traffic sign recognition using efficient convolutional neural network. IEEE Access 7:53330–53346
Bengio Y (2012) Practical recommendations for gradient-based training of deep architectures. Neural Netw TricksTrade:437–478
Bi Q, Qin K, Zhang H, Li Z, Xu K (2020) RADC-Net: a residual attention based convolution network for aerial scene classification. Neurocomputing 377:345–359
Cheng G, Li R, Lang C, Han J (2021) Task-wise attention guided part complementary learning for few-shot image classification. Sci China Inf Sci 64(2):1–14
Cheng G, Yang C, Yao X, Guo L, Han J (2018) When deep learning meets metric learning: remote sensing image scene classification via learning discriminative CNNs. IEEE Geosci Remote Sens Lett 56(5):2811–2821
Chu X, Yang W, Ouyang W, Ma C, Yuille AL, Wang X (2017) Multi-context attention for human pose estimation. 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp 5669–5678
Chung JH, Kim DW, Kang TK, Lim MT (2020) Traffic sign recognition in harsh environment using attention based convolutional pooling neural network. Neural Process Lett 51:2551–2573
Ciresan D, Meier U, Masci J, Schmidhuber J (2011) A committee of neural networks for traffic sign classification. The 2011 International Joint Conference on Neural Networks, pp 1918–1921
Ciresan D, Meier U, Masci J, Schmidhuber J (2012) Multi-column deep neural network for traffic sign classification. Neural Netw 32:333–338
Ding X, Guo Y, Ding G, Han J (2019) ACNet: strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks. Proceedings of the IEEE/CVF, International Conference on Computer Vision (ICCV), pp 1911–1920
Du W, Wang Y, Qiao Y (2018) Recurrent spatial-temporal attention network for action recognition in videos. IEEE Trans Image Process 27(3):1347–1360
Farabet C, Couprie C, Najman L, LeCun Y (2013) Learning hierarchical features for scene labeling. IEEE Trans Pattern Anal Mach Intell 35 (8):1915–1929
Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, Lu H (2019) Dual attention network for scene segmentation. Proceedings of the IEEE/CVF, Conference on Computer Vision and Pattern Recognition (CVPR), pp 3146–3154
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. Proc IEEE Conf Comput Vis Pattern Recognit:580–587
Gudigar A, Chokkadi S, Raghavendra U, Acharya UR (2019) An efficient traffic sign recognition based on graph embedding features. Neural Comput Appl 31(2):395–407
Hamker FH (2004) Predictions of a model of spatial attention using sum-and max-pooling functions. Neurocomputing 56:329–343
Haque WA, Arefin S, Shihavuddin ASM, Hasan MA (2021) DeepThin: a novel lightweight CNN architecture for traffic sign recognition without GPU requirements. Expert Syst Appl 168:114481
Hechri A, Mtibaa A (2020) Two-stage traffic sign detection and recognition based on SVM and convolutional neural networks. IET Image Process 14 (5):939–946
Hong IP, Hwang YB, Kim DY (2019) Efficient deep learning of image denoising using patch complexity local divide and deep conquer. Pattern Recogn 96:106945
Huang G, Liu Z, Maaten LVD, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3431–3440
Huang Z, Wang X, Huang L, Huang C, Wei Y, Liu W (2019) CCNet: criss-cross attention for semantic segmentation. Proceedings of the IEEE/CVF, International Conference on Computer Vision (ICCV), pp 603–612
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. Int Conf Mach Learn:448–456
Ji Y, Zhang H, Jie Z, Ma L, Wu QMJ (2020) CASNet: a cross-attention siamese network for video salient object detection. IEEE Trans Neural Netw Learn Syst:1–15
Jin J, Fu K, Zhang C (2014) Traffic sign recognition with hinge loss trained convolutional neural networks. IEEE Trans Intell Trans Syst 15:1991–2000
Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems. [Online]. Available: http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf, vol 25. Curran Associates, Inc., pp 1097–1105
Lateef F, Ruichek Y (2019) Survey on semantic segmentation using deep learning techniques. Neurocomputing 338:321–348
Li X, Jie Z, Feng J, Liu C, Yan S (2018) Learning with rethinking: recurrently improving convolutional neural networks through feedback. Pattern Recogn 79:183–194
Liu C, Chang F, Chen Z, Liu D (2016) Fast traffic sign recognition via high-contrast region extraction and extended sparse representation. IEEE Trans Intell Trans Syst 17(1):79–92
Liu Z, Du J, Tian F, Wen J (2019) MR-CNN: a multi-scale region-based convolutional neural network for small traffic sign recognition. IEEE Access 7:57120–57128
Liu J, Wang Y, Li Y, Fu J, Li J, Lu H (2018) Collaborative deconvolutional neural networks for joint depth estimation and semantic segmentation. IEEE Trans Neural Netw Learn Syst 29(11):5655–5666
Liu D, Wen B, Jiao J, Liu X, Wang Z, Huang TS (2020) Connecting image denoising and high-level vision tasks via deep learning. IEEE Trans Image Process 29:3695–3706
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3431–3440
Lu X, Wang W, Ma C, Shen J, Shao L, Porikli F (2019) See more, know more: unsupervised video object segmentation with co-attention siamese networks. Proceedings of the IEEE/CVF, Conference on Computer Vision and Pattern Recognition (CVPR), pp 3623–3632
Lu X, Wang W, Shen J, Crandall DJ, Gool LV (2021) Segmenting objects from relational visual data. IEEE Trans Pattern Anal Mach Intell
Lu X, Wang Y, Zhou X, Zhang Z, Ling Z (2017) Traffic sign recognition via multi-modal tree-structure embedded multi-task learning. IEEE Trans Intell Trans Syst 18(4):960–972
Luo H, Yang Y, Tong B, Wu F, Fan B (2018) Traffic sign recognition using a multi-task convolutional neural network. IEEE Trans Intell Trans Syst 19(4):1100–1111
Mao T, Zhang Y, Ruan Y, Gao H, Zhou H, Li D (2018) Feature learning and process monitoring of injection molding using convolution-deconvolution auto encoders. Comput Chem Eng 118:77–90
Mhalla A, Chateau T, Amara NEB (2019) Spatio-temporal object detection by deep learning: video-interlacing to improve multi-object tracking. Image Vis Comput 88:120–131
Mogelmose A, Trivedi MM, Moeslund TB (2012) Vision-based traffic sign detection and analysis for intelligent driver assistance systems: perspectives and survey. IEEE Trans Intell Trans Syst 13(4):1484–1497
Noh HW, Hong SH, Han BH (2015) Learning deconvolution network for semantic segmentation. Proceedings of the IEEE international conference on computer vision, pp 1520–1528
Noord N, Postma E (2017) Learning scale-variant and scale-invariant features for deep image classification. Pattern Recogn 61:583–592
Pang Y, Sun M, Jiang X, Li X (2018) Convolution in convolution for network in network. IEEE Trans Neural Netw Learn Syst 29(5):1587–1597
Saedi SI, Khosravi H (2020) A deep neural network approach towards real-time on-branch fruit recognition for precision horticulture. Expert Syst Appl 159:345–359
Scherer D, Muller A, Behnke S (2010) Evaluation of pooling operations in convolutional architectures for object recognition. Int Conf Artif Neural Netw, pp 92–101
Sermanet P, LeCun Y (2011) Traffic sign recognition with multi-scale convolutional networks, Neural Networks (IJCNN). The 2011 International Joint Conference on, pp 2809–2813
Sharma S, Kiros R, Salakhutdinov R (2016) Action recognition using visual attention, arXiv:1511.04119
Shen J, Ropbertson N (2021) BBAS: Towards large scale effective ensemble adversarial attacks against deep neural network learning. Inf Sci 569:469–478
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556
Springenberg JT, Dosovitskiy A, Brox T, Riedmiller M (2014) Striving for simplicity: the all convolutional net, arXiv:1412.6806
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Stallkamp J, Schlipsing M, Salmen J, lgel C (2012) Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw 32:323–332
Stollenga M, Masci J, Gomez F, Schmidhuber J (2014) Design of stabilizing state feedback for delay systems via convex optimization. In: Advances in neural information processing systems, pp 3545–3553
Sun M, Song Z, Jiang X, Pan J, Pang Y (2017) Learning pooling for convolutional neural network. Neurocomputing 224:96–104
Szegedy C, Vanhoucke V, Ioffe S, Shlens J (2015) Going deeper with convolutions. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1–9
Tabernik D, Skocaj D (2020) Deep learning for large-scale traffic-sign detection and recognition. IEEE Trans Intell Trans Syst 21(4):1427–1440
Timofte R, Zimmermann K, Gool LV (2021) Multi-view traffic sign detection, recognition, and 3D localisation. Mach Vis Appl 25(3):633–647
Vidnerova P, Neruda R (2020) Vulnerability of classifiers to evolutionary generated adversarial examples. Neural Netw 127:168–181
Wang W, Lu X, Shen J, Crandall DJ, Shao L (2019) Zero-shot video object segmentation via attentive graph neural networks. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp 9236–9245
Wickramasinghe CS, Amarasinghe K, Manic M (2019) Deep self-organizing maps for unsupervised image classification. IEEE Trans Ind Informat 15 (11):5837–5845
Wojna Z, Gorban A, Lee DS, Murphy K, Yu Q, Li Y, Ibarz J (2017) Attention-based extraction of structured information from street view imagery, arXiv:1704.03549
Wong A, Shafiee MJ, Jules MS (2018) Micronnet: a highly compact deep convolutional neural network architecture for real-time embedded traffic sign classification. IEEE Access 6:59 803–59 810
Yan Z, Feng Y, Cheng C, Fu J, Zhou X, Yuan J (2018) Extensive exploration of comprehensive vehicle attributes using D-CNN with weighted multi-attribute strategy. IET Intell Transp Syst 12(3):186–193
Yang S, Deng B, Wang J, Li H, Lu M, Che Y, Wei X, Loparo KA (2020) Scalable digital neuromorphic architecture for large-scale biophysically meaningful neural network with multi-compartment neurons. IEEE Trans Neural Netw Learn Syst 31(1):148–162
Yang S, Deng B, Wang J, Liu C, Li H, Lin Q, Fietkiewicz C, Loparo KA (2019) Design of hidden-property-based variable universe fuzzy control for movement disorders and its efficient reconfigurable implementation. IEEE Trans Fuzzy Syst 27(2):304–318
Yang S, Gao T, Wang J, Deng B, Lansdell B, Linares-Barranco B (2021) Efficient spike-driven learning with dendritic event-based processing. Front Neurosci 15:97
Yang S, Wang J, Deng B, Azghadi MR, Linares-Barranco B (2021) Neuromorphic context-dependent learning framework with fault-tolerant spike routing. IEEE Trans Neural Netw Learn Syst
Yang S, Wei X, Deng B, Liu C, Li H, Wang J (2018) Efficient digital implementation of a conductance-based globus pallidus neuron and the dynamics analysis. Physica A: Stat Mech Appl 494:484–502
Yuan Y, Xiong Z, Wang Q (2019) VSSA-NET: vertical Spatial sequence attention network for traffic sign detection. IEEE Trans Image Process 28 (7):3423–3434
Zeiler MD, Fergus R (2013) Stochastic pooling for regularization of deep convolutional neural networks, arXiv:1301.3557, pp 2278–2324
Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process 26(7):3142–3155
Acknowledgements
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2016R1D1A1B01016071 and NRF-2017R1D1A1B03031467).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of Interests
The authors declare that there is no conflict of interest regarding the publication of this paper.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chung, J.H., Kim, D.W., Kang, T.K. et al. ADM-Net: attentional-deconvolution module-based net for noise-coupled traffic sign recognition. Multimed Tools Appl 81, 23373–23397 (2022). https://doi.org/10.1007/s11042-022-12219-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12219-1