Optimizing Transfer Learning and Fine-Tuning Hyperparameters in Image Classification Problems with Firefly Algorithm

• Vinícius T. M. G. da Silva UFV
• Gustavo F. V. de Oliveira UFV
• Fabrício A. Silva UFV
• Marcus H. S. Mendes UFV

DOI: https://doi.org/10.5753/eniac.2024.245032

Resumo

Image classification is crucial in computer vision, mainly with Convolutional Neural Networks (CNNs). This paper optimizes transfer learning and fine-tuning hyperparameters of CNNs pre-trained on ImageNet for still image classification. Hyperparameter tuning is a complex task that impacts the classification results. The Firefly Algorithm (FA) was used to optimize these hyperparameters across four datasets with Xception and ResNet-152 architectures. Experiments show that FA enhances model performance, achieving state-of-the-art accuracy on three datasets: Multi-Class Weather (99.11%), Pistachio (100%), and D0 (99.89%). Despite being time-consuming, this approach offers a viable method for improving image classification, mainly with smaller datasets.

Palavras-chave: Firefly Algorithm, Transfer Learning, Image Classification

Referências

Al-Haija, Q. A., Smadi, M. A., and Zein-Sabatto, S. (2020). Multi-class weather classification using resnet-18 cnn for autonomous iot and cps applications. In 2020 International Conference on Computational Science and Computational Intelligence (CSCI), pages 1586–1591.

Aszemi, N. M. and Dominic, P. (2019). Hyperparameter optimization in convolutional neural network using genetic algorithms. International Journal of Advanced Computer Science and Applications, 10(6).

Avuçlu, E. (2023). Classification of pistachio images with the resnet deep learning model. Selcuk Journal of Agriculture and Food Sciences, 37(2):291–300.

Ayan, E. (2023). Genetic algorithm-based hyperparameter optimization for convolutional neural networks in the classification of crop pests. Arabian Journal for Science and Engineering, 49(3):3079–3093.

Ayan, E., Erbay, H., and Varçın, F. (2020). Crop pest classification with a genetic algorithm-based weighted ensemble of deep convolutional neural networks. Computers and Electronics in Agriculture, 179:105809.

Bacanin, N., Bezdan, T., Venkatachalam, K., and Al-Turjman, F. (2021). Optimized convolutional neural network by firefly algorithm for magnetic resonance image classification of glioma brain tumor grade. Journal of Real-Time Image Processing, 18(4):1085–1098.

Bacanin, N., Stoean, C., Zivkovic, M., Rakic, M., Strulak-Wójcikiewicz, R., and Stoean, R. (2023). On the benefits of using metaheuristics in the hyperparameter tuning of deep learning models for energy load forecasting. Energies, 16(3).

Behera, N., Das, S., Singh, A. P., Swain, A. K., and Rout, M. (2024). Cnn - based medical image classification models for the identification of pneumonia and malaria. In 2024 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC), pages 01–06.

Belete, D. and D H, M. (2021). Grid search in hyperparameter optimization of machine learning models for prediction of hiv/aids test results. International Journal of Computers and Applications, 44:1–12.

Bianco, S., Cadene, R., Celona, L., and Napoletano, P. (2018). Benchmark analysis of representative deep neural network architectures. IEEE Access, 6:64270–64277.

Bloedorn, F. G. and Webber, C. G. (2023). Transfer learning applied to a classification task: a case study in the footwear industry. IEEE Latin America Transactions, 21(3):427–433.

Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions.

Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255.

Gbeminiyi, A. (2018). Multi-class weather dataset for image classification. Mendeley Data, 6:15–23.

Gesmundo, A. (2022). A continual development methodology for large-scale multitask dynamic ml systems.

Golnoori, F., Boroujeni, F. Z., and Monadjemi, A. (2023). Metaheuristic algorithm based hyper-parameters optimization for skin lesion classification. Multimedia Tools and Applications, 82(17):25677–25709.

He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep residual learning for image recognition.

Lai, W., Kuang, M., Wang, X., Ghafariasl, P., Sabzalian, M. H., and Lee, S. (2023). Skin cancer diagnosis (scd) using artificial neural network (ann) and improved gray wolf optimization (igwo). Scientific Reports, 13(1):19377.

Li, C., Jiang, J., Zhao, Y., Li, R., Wang, E., Zhang, X., and Zhao, K. (2022). Genetic algorithm based hyper-parameters optimization for transfer convolutional neural network. In International Conference on Advanced Algorithms and Neural Networks (AANN 2022), volume 12285, pages 232–241. SPIE.

Lisda, L., Kusrini, K., and Ariatmanto, D. (2023). Classification of pistachio nut using convolutional neural network. Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, 8(1):71–77.

Mishra, S. (2021). Malaria parasite detection using efficient neural ensembles. Journal of Electronics, Electromedical Engineering, and Medical Informatics, 3(3):119–133.

Mohamed, A., Hemeida, A., and Hassan, M. (2022). Image classification based deep learning: A review. Aswan University Journal of Sciences and Technology, 2.

Mujahid, M., Rustam, F., Shafique, R., Montero, E. C., Alvarado, E. S., de la Torre Diez, I., and Ashraf, I. (2024). Efficient deep learning-based approach for malaria detection using red blood cell smears. Scientific Reports, 14(1):13249.

Nanni, L., Manfè, A., Maguolo, G., Lumini, A., and Brahnam, S. (2022). High performing ensemble of convolutional neural networks for insect pest image detection. Ecological Informatics, 67:101515.

Narayanan, B. N., de Silva, M. S., and Hardie, R. C. (2023). A patient specific algorithm for plasmodium malaria detection on cell images. In NAECON 2023 - IEEE National Aerospace and Electronics Conference, pages 258–262.

Ozkan, I., Koklu, M., and Saraçoğlu, R. (2021). Classification of pistachio species using improved k-nn classifier. Health, 23:e2021044.

Rajaraman, S., Antani, S. K., Poostchi, M., Silamut, K., Hossain, M. A., Maude, R. J., Jaeger, S., and Thoma, G. R. (2018). Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images. PeerJ, 6:e4568.

Saranya, T., Deisy, C., and Sridevi, S. (2024). Efficient agricultural pest classification using vision transformer with hybrid pooled multihead attention. Computers in Biology and Medicine, 177:108584.

Schwarz Schuler, J. P., Also, S. R., Puig, D., Rashwan, H., and Abdel-Nasser, M. (2022). An enhanced scheme for reducing the complexity of pointwise convolutions in cnns for image classification based on interleaved grouped filters without divisibility constraints. Entropy, 24(9).

Sibinraj, V., Gafoor, F., Anandhu, P., and Anoop, V. (2024). Automated malaria cell image classification using convolutional neural networks. TechRxiv.

Singh, D., Taspinar, Y. S., Kursun, R., Cinar, I., Koklu, M., Ozkan, I. A., and Lee, H.-N. (2022). Classification and analysis of pistachio species with pre-trained deep learning models. Electronics, 11(7).

Snoek, J., Larochelle, H., and Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms.

Tian, M., Chen, X., Zhang, H., Zhang, P., Cao, K., and Wang, R. (2021). Weather classification method based on spiking neural network. In 2021 International Conference on Digital Society and Intelligent Systems (DSInS), pages 134–137.

Ung, H. T., Ung, H. Q., and Nguyen, B. T. (2021). An efficient insect pest classification using multiple convolutional neural network based models.

Xie, C., Wang, R., Zhang, J., Chen, P., Dong, W., Li, R., Chen, T., and Chen, H. (2018). Multi-level learning features for automatic classification of field crop pests. Computers and Electronics in Agriculture, 152:233–241.

Yang, X.-S. (2010). Nature-Inspired Metaheuristic Algorithms. Luniver Press.