Skip to main content
Log in

CNN-RDM: a new image processing model for improving the structure of deep learning based on representational dissimilarity matrix

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Convolutional neural networks (CNNs) are widely used to categorize images. Successful training of a CNN requires rapid convergence of its weights, which increases the efficiency of training. In this paper, a CNN-RDM model, based on CNN and representational dissimilarity matrix (RDM), is proposed. In the proposed model, a loss function is defined in the RDM whose output is a minimized dissimilarity matrix. Therefore, by combining this minimized matrix of RDM loss function with CNN cross-entropy, the final output is minimized. The inputs of CNN-RDM model are pixels with low-level features, and the output is a set of features. The CNN-RDM model can actually change the structure of the neural network inspired by the visual pathway. The performance of our model is evaluated using 50 batches, including 10 image classes, each containing 5 samples on the data sets Cifar10, Cifar100, and Coco. Evaluation results demonstrate that our CNN-RDM model has achieved an accuracy of 60% in image classification, which is superior to 51% accuracy of the obtained model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Khallaf R, Khallaf M (2021) Classification and analysis of deep learning applications in construction: a systematic literature review. Automation in Construc 129:103760

    Article  Google Scholar 

  2. Momeny M, Sarram MA, Latif AM, Sheikhpour R, Zhang YD (2021) A noise robust convolutional neural network for image classification. Results in Eng, p. 100225

  3. Shariati M, Mafipour MS, Haido JH, Yousif ST, Toghroli A, Trung NT, Shariati A (2020) Identification of the most influencing parameters on the properties of corroded concrete beams using an Adaptive Neuro-Fuzzy Inference System (ANFIS). Steel Compos Struct 34(1):155

    Google Scholar 

  4. Liu L, Wang Z, Qiu T, Chen Q, Lu Y, Suen CY (2021) Document image classification: progress over two decades. Neurocomputing 453:223–240

    Article  Google Scholar 

  5. Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117

    Article  Google Scholar 

  6. Yan LC, Yoshua B, Geoffrey H (2015) Deep learning. Nature 521(7553):436–444

    Article  Google Scholar 

  7. Volokitin A, Roig G, Poggio T (2017) Do deep neural networks suffer from crowding?. arXiv preprint arXiv:1706.08616

  8. Helie S, Ashby FG (2012) Learning and transfer of category knowledge in an indirect categorization task. Psychol Res 76(3):292–303

    Article  Google Scholar 

  9. Stettler M, Francis G (2018) Using a model of human visual perception to improve deep learning. Neural Netw 104:40–49

    Article  Google Scholar 

  10. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition, In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778

  11. He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks, In: European Conference on Computer Vision, pp. 630-645

  12. Fong RC, Scheirer WJ, Cox DD (2018) Using human brain activity to guide machine learning. Sci Rep 8(1):5397

    Article  Google Scholar 

  13. Zhang M, Li W, Du Q (2018) Diverse region-based CNN for hyper spectral image classification. IEEE Trans Image Process 27(6):2623–2634

    Article  MATH  Google Scholar 

  14. Gong Z, Zhong P, Yu Y, Hu W, Li S (2019) A CNN with multi scale convolution and diversified metric for hyper spectral image classification. IEEE Trans Geosci Remote Sens 57(6):3599–3618

    Article  Google Scholar 

  15. Pei Y, Huang Y, Zou Q, Zhang X, Wang S (2019) Effects of image degradation and degradation removal to cnn-based image classification. IEEE transactions on pattern analysis and machine intelligence

  16. Gour M, Jain S, Sunil Kumar T (2020) Residual learning based CNN for breast cancer histopathological image classification. Int J Imag Syst Technol 30(3):621–635

    Article  Google Scholar 

  17. Wang J, Song X, Sun L, Huang W, Wang J (2020) A novel cubic convolutional neural network for hyperspectral image classification. IEEE J Selected Topics in Appl Earth Observ Remote Sens 13:4133–4148

    Article  Google Scholar 

  18. Kaur T, Gandhi TK (2020) Deep convolutional neural networks with transfer learning for automated brain image classification. Mach Vis Appl 31(3):1–16

    Article  Google Scholar 

  19. Tong K, Wu Y, Zhou F (2020) Recent advances in small object detection based on deep learning: a review. Image and Vis Comput 97:103910

    Article  Google Scholar 

  20. Popat P, Sheth P, Jain S (2019) Animal/object identification using deep learning on raspberry pi. In Information and Communication Technology for Intelligent Systems (pp. 319-327). Springer, Singapore

  21. Guo Y, Chen Y, Tan M, Jia K, Chen J, Wang J (2021) Content-aware convolutional neural networks. Neural Netw 143:657–668

    Article  Google Scholar 

  22. Guo Q, Wu XJ, Kittler J, Feng Z (2020) Self-grouping convolutional neural networks. Neural Netw 132:491–505

    Article  Google Scholar 

  23. Qin X, Zhang Z, Huang C, Dehghan M, Zaiane OR, Jagersand M (2020) U2-Net: Going deeper with nested U-structure for salient object detection. Pattern Recogn 106:107404

    Article  Google Scholar 

  24. Tek FB, Çam İ, Karlı D (2021) Adaptive convolution kernel for artificial neural networks. J Vis Commun Image Represent 75:103015

    Article  Google Scholar 

  25. Paoletti ME, Tao X, Haut JM, Moreno-Álvarez S, Plaza A (2021) Deep mixed precision for hyperspectral image classification. The Journal of Supercomputing, pp. 1-12

  26. Yu J, Liu H, Zheng X (2019) Two-dimensional joint local and nonlocal discriminant analysis-based 2D image feature extraction for deep learning. Neural Comput Appl, pp.1-16

  27. Lateef F, Ruichek Y (2019) Survey on semantic segmentation using deep learning techniques. Neurocomputing 338:321–348

    Article  Google Scholar 

  28. Wang J, Liu T, Wang X (2020) Human hand gesture recognition with convolutional neural networks for K-12 double-teachers instruction mode classroom. Infrared Phys Technol 111:103464

    Article  Google Scholar 

  29. Sultana F, Sufian A, Dutta P (2018) Advancements in image classification using convolutional neural network. In 2018 Fourth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN) (pp. 122-129). IEEE

  30. Deng L (2014) A tutorial survey of architectures, algorithms, and applications for deep learning. APSIPA Transactions on Signal and Information Processing, p. 3

  31. Hussain M, Bird JJ, Faria DR (2018) A study on CNN transfer learning for image classification. In: UK Workshop on computational Intelligence (pp. 191-202). Springer, Cham

  32. Garea AS, Heras DB, Argüello F (2019) Caffe CNN-based classification of hyperspectral images on GPU. J Supercomput 75(3):1065–1077

    Article  Google Scholar 

  33. Heidari M, Mirniaharikandehei S, Khuzani AZ, Danala G, Qiu Y, Zheng B (2020) Improving the performance of CNN to predict the likelihood of COVID-19 using chest X-ray images with preprocessing algorithms. Int J Med Inform 144:104284

    Article  Google Scholar 

  34. Seifi S, Tuytelaars T (2019) How to improve CNN-based 6-DoF camera pose estimation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (pp. 0-0)

  35. Caldelli R, Becarelli R, Carrara F, Falchi F, Amato G (2019) Exploiting CNN layer activations to improve adversarial image classification. In: 2019 IEEE International Conference on Image Processing (ICIP) (pp. 2289-2293). IEEE

  36. Qin J, Pan W, Xiang X, Tan Y, Hou G (2020) A biological image classification method based on improved CNN. Ecolog Inform 58:101093

    Article  Google Scholar 

  37. Satapathy P, Pradhan SK, Hota S, Mahakud RR (2021) Brain Image Classification Using the Hybrid CNN Architecture. In Advances in Intelligent Computing and Communication (pp. 329-336). Springer, Singapore

  38. Vaddi R, Manoharan P (2020) Hyper spectral image classification using CNN with spectral and spatial features integration. Infrared Phys Technol 107:103296

    Article  Google Scholar 

  39. Gill HS, Khehra BS (2021) An integrated approach using CNN-RNN-LSTM for classification of fruit images. Materials Today: Proceedings

  40. Sun Y, Xue B, Zhang M, Yen GG, Lv J (2020) Automatically designing CNN architectures using the genetic algorithm for image classification. IEEE Trans Cybernet 50(9):3840–3854

    Article  Google Scholar 

  41. Brownlee J (2019) Impact of dataset size on deep learning model skill and performance estimates. Machine Learning Mastery, 6: arxiv

  42. Yamashita R, Nishio M, Do RKG, Togashi K (2018) Convolutional neural networks: an overview and application in radiology. Insights into Imag 9(4):611–629

    Article  Google Scholar 

  43. Han D, Liu Q, Fan W (2018) A new image classification method using CNN transfer learning and web data augmentation. Exp Syst Appl 95:43–56

    Article  Google Scholar 

  44. Diedrichsen J, Berlot E, Mur M, Schütt H H, Shahbazi M, Kriegeskorte N (2020) Comparing representational geometries using whitened unbiased-distance-matrix similarity. arXiv preprint arXiv:2007.02789

  45. Wan L, Wang Q, Papir A, Moreno IL (2018) Generalized end-to-end loss for speaker verification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4879-4883). IEEE

  46. Rao D, McMahan B (2019) Natural language processing with PyTorch: build intelligent language applications using deep learning. O’Reilly Media, Inc.

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Seyed Mohammad Jalal Rastegar Fatemi.

Ethics declarations

Conflict of interest

We have no conflict of interest to declare.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Heydaran Daroogheh Amnyieh, Z., Rastegar Fatemi, S.M.J., Rastgarpour, M. et al. CNN-RDM: a new image processing model for improving the structure of deep learning based on representational dissimilarity matrix. J Supercomput 79, 4266–4290 (2023). https://doi.org/10.1007/s11227-022-04661-7

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-022-04661-7

Keywords

Navigation