Multi-stage fine-tuning of EfficientNetV2-S for material recognition on edge devices
References
- P. Thielmann, Y. Zhou, B. Mirbach, D. Stricker and J. Rambach, “A review of computer vision for industrial-grade waste classification,” IEEE Access, vol. 13, pp. 151934–151953, 2025.
- E. Adán and A. Adán, “Computer vision for glass waste: Technologies and sensors,” Sensors, vol. 25, no. 21, pp. 6634, 2025.
- M. Tan and Q. Le, “EfficientNetV2: Smaller models and faster training,” in Proc. Int. Conf. Machine Learning (ICML), PMLR, Jul. 2021, pp. 10096–10106.
- Z. Zhao, E. B. A. Bakar, N. B. A. Razak, et al., “Progressive optimization of EfficientNetV2 for classification based on images of corroded objects,” Comp. Appl. Math., vol. 44, p. 419, 2025.
- T. Njoroge, R. Kibuku, and K. Mugoye, “Comparative and edge-hybrid modeling of EfficientNetV2 and MobileNetV2 for multi-class crop disease classification with statistical validation,” J. Edge Comput., vol. 4, no. 2, pp. 234–262, 2025.
- E. Mengiste, K. R. Mannem, S. A. Prieto, and B. García de Soto, “Transfer-learning and texture features for recognition of the conditions of construction materials with small data sets,” J. Comput. Civ. Eng., vol. 38, no. 1, pp. 04023036, 2024.
- P. Wieschollek and H. Lensch, “Transfer learning for material classification using convolutional networks,” arXiv preprint arXiv:1609.06188, 2016. Available: https://arxiv.org/abs/1609.06188
- A. Sticlaru, “Material classification using neural networks,” arXiv preprint arXiv:1710.06854, 2017. Available: https://arxiv.org/abs/1710.06854
- Y. Zhang, M. Ozay, X. Liu, and T. Okatani, “Integrating deep features for material recognition,” in Proc. 23rd Int. Conf. Pattern Recognit. (ICPR), IEEE, Dec. 2016, pp. 3697–3702.
- Y. Rayhan and A. P. Rifai, “Multi-class waste classification using convolutional neural network,” Appl. Environ. Res., vol. 46, no. 2, 2024.
- M. A. H. Khan, H. Sabnis, J. A. A. Jothi, J. Kanishkha, and A. D. Prasad, “Classification of microstructure images of metals using transfer learning,” in Proc. Int. Conf. Modelling and Development of Intelligent Systems, Cham: Springer Nature Switzerland, Oct. 2022, pp. 136–147.
- M. Malik, S. Sharma, M. Uddin, C. L. Chen, C. M. Wu, P. Soni, and S. Chaudhary, “Waste classification for sustainable development using image recognition with deep learning neural network models,” Sustainability, vol. 14, no. 12, p. 7222, Jun. 2022.
- K. Liu and X. Liu, “Recycling material classification using convolutional neural networks,” in Proc. 21st IEEE Int. Conf. Machine Learning and Applications (ICMLA), Dec. 2022, pp. 83–88.
- L. Sharan, R. Rosenholtz, and E. H. Adelson, “Accuracy and speed of material categorization in real-world images,” J. Vis., vol. 14, no. 9, pp. 12, 2014.
- Ultralytics, “YOLOv8 – You Only Look Once, Version 8,” 2023. Available: https://github.com/ultralytics/ultralytics. [Accessed: Jun. 01, 2025].
- J. Nikolić, S. Tomić, Z. Perić, A. Jovanović, and D. Aleksić, “Accuracy degradation aware bit rate allocation for layer-wise uniform quantization of weights in neural network,” J. Electr. Eng., vol. 75, no. 6, pp. 425–434, 2024.
- Y. Bengio, “Deep learning of representations for unsupervised and transfer learning,” in Proc. ICML Workshop on Unsupervised and Transfer Learning, JMLR W&CP, Jun. 2012, pp. 17–36.
- J. Howard and S. Gugger, “Fastai: A layered API for deep learning,” Information, vol. 11, no. 2, p. 108, 2020.
- M. Kornblith, J. Shlens, and Q. Le, “Do better ImageNet models transfer better?,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2019, pp. 2661–2671.
- C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 2818–2826.
- L. Prechelt, “Early stopping – but when?,” in Neural Networks: Tricks of the Trade, Berlin, Heidelberg: Springer, 2002, pp. 55–69.
- J. Kirkpatrick et al., “Overcoming catastrophic forgetting in neural networks,” Proc. Natl. Acad. Sci., vol. 114, no. 13, pp. 3521–3526, 2017.
- L. N. Smith, “Cyclical learning rates for training neural networks,” in Proc. IEEE Winter Conf. Appl. Comput. Vis. (WACV), Mar. 2017, pp. 464–472.
- M. Abadi et al., “TensorFlow: A system for large-scale machine learning,” in Proc. USENIX Symp. Operating Systems Design and Implementation (OSDI), 2016, pp. 265–283.
Language: English
Page range: 123 - 129
Submitted on: Feb 4, 2026
Published on: Apr 18, 2026
Published by: Slovak University of Technology in Bratislava
In partnership with: Paradigm Publishing Services
Publication frequency: 6 issues per year
Keywords:
Related subjects:
© 2026 Stefan Tomić, Dhabia Aldhuhoori, Turker Turker, Jelena Nikolić, Zoran Perić, Riccardo Zese, published by Slovak University of Technology in Bratislava
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.