A Study on Small-Scale Snake Image Classification Based on Improved SimCLR
Source abstract
Abstract
The exotic pet trade is a major driver of alien species invasions. Improper introductions or a lack of management can result in severe ecological consequences. Therefore, accurate identification of exotic pets is essential for the prevention and early warning of species invasions. This paper proposes a novel recognition method for fine-grained images of small-scale exotic pet snakes in complex backgrounds based on an improved SimCLR framework. A hierarchical window attention mechanism is introduced into the encoder network to enhance feature extraction. In the loss function, a supervised contrastive mechanism is introduced to exclude false negative samples using label information, which helps reduce representation noise and enhance training stability. The training strategy incorporates random erasing and random grayscale data augmentation techniques to improve performance further. The projection head is constructed using a two-layer multilayer perceptron (MLP), and the cosine annealing schedule combined with the AdamW optimizer is adopted for learning rate adjustment. Experimental results on a self-constructed dataset demonstrate that the proposed model achieves a recognition accuracy of 97.5%, outperforming existing baseline models. This study fills a gap in exotic pet snake classification and provides a practical tool for species invasion prevention and early detection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image Processing Techniques and Applications · Digital Imaging for Blood Diseases
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China
References (34)
Show source-provided references
1. Roy, H.E. (2023). IPBES Invasive Alien Species Assessment: Summary for Policymakers. Zenodo.
2. Research Progress on the Impact of Invasive Alien Vertebrates on Biodiversity
3. Current Status and Prevention System Construction of Invasive Alien Species: A Global Perspective and China’s Case
4. Distribution Pattern of Invasive Alien Animals in China and Its Relationship with Environmental Factors and Human Activities
5. An Efficient DenseNet-Based Deep Learning Model for Big-4 Snake Species Classification10.1016/j.toxicon.2024.107744 ↗
6. Bolon, I., Picek, L., Durso, A.M., Alcoba, G., Chappuis, F., and Ruiz de Castañeda, R. (2022). An Artificial Intelligence Model to Identify Snakes from Across the World: Opportunities and Challenges for Global Health and Herpetology. PLoS Negl. Trop. Dis., 16.10.2139/ssrn.4010876 ↗
7. Discriminative Histogram Taxonomy Features for Snake Species Identification10.1186/s13673-014-0003-0 ↗
8. Progga, N.I., Rezoana, N., Hossain, M.S., Islam, R.U., and Andersson, K. (2021). A CNN-Based Model for Venomous and Non-Venomous Snake Classification. Analogical and Inductive Inference, Springer. Available online: https://api.semanticscholar.org/CorpusID:236963195.10.1007/978-3-030-82269-9_17 ↗
9. Hu, F., Wang, P., Li, Y., Duan, C., Zhu, Z., Wang, F., Zhang, F., Li, Y., and Wei, X.-S. (2023). Watch Out Venomous Snake Species: A Solution to SnakeCLEF2023. arXiv.
10. Zou, C., Xu, F., Wang, M., Li, W., and Cheng, Y. (2022). Solutions for Fine-Grained and Long-Tailed Snake Species Recognition in SnakeCLEF 2022. arXiv.
11. Bloch, L., and Friedrich, C. (2021, January 21–24). EfficientNets and Vision Transformers for Snake Species Identification Using Image and Location Information. Proceedings of the Conference and Labs of the Evaluation Forum (CLEF 2021), Bucharest, Romania. Available online: https://api.semanticscholar.org/CorpusID:237298186.
12. Sani, N.M., and Satpute, R.S. (2024, January 27–28). Review on Snake Species Identification on Snake Bite Marks Using Deep Learning. Proceedings of the 2024 IEEE 3rd World Conference on Applied Intelligence and Computing (AIC), Gwalior, India. Available online: https://api.semanticscholar.org/CorpusID:273693704.10.1109/AIC61668.2024.10731020 ↗
13. Borsodi, R., and Papp, D. (2021, January 21–24). Incorporation of Object Detection Models and Location Data into Snake Species Classification. Proceedings of the Conference and Labs of the Evaluation Forum, Bucharest, Romania. Available online: https://api.semanticscholar.org/CorpusID:237298891.
14. Artificial Intelligence-Based Snakebite Identification Using Snake Images, Snakebite Wound Images, and Other Modalities of Information: A Systematic Review10.1016/j.ijmedinf.2023.105024 ↗
15. Snake Species Classification Using Deep Learning Techniques10.1007/s11042-023-16773-0 ↗
16. Fu, Y. (2019). Research on Snake Image Classification Based on Deep Learning. [Master’s Thesis, Zhejiang University].
17. Durso, A.M., Moorthy, G.K., Mohanty, S.P., Bolon, I., Salathé, M., and Ruiz de Castañeda, R. (2021). Supervised Learning Computer Vision Benchmark for Snake Species Identification From Photographs: Implications for Herpetology and Global Health. Front. Artif. Intell., 4.10.3389/frai.2021.582110 ↗
18. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., and Houlsby, N. (2021). An Image Is Worth 16×16 Words: Transformers for Image Recognition at Scale. arXiv.
19. Fine-Grained Classification of Wild Snakes Based on Self-Attention Siamese Network
20. Huang, L., Fu, S., Di, Y., Zhang, L., Zhou, J., and Sun, X. (2022, January 5–8). Snake Species Recognition Using Multi-Modal Ensemble and Meta-Learning. Proceedings of the CLEF 2022: Conference and Labs of the Evaluation Forum, Bologna, Italy. Available online: https://ceur-ws.org/Vol-3180/paper-178.pdf.
21. Hu, Q., Hu, J., Fu, S., and Huang, L. (2023, January 18–21). CLIP-based Multimodal Fusion and Long-tail Learning for SnakeCLEF2023. Proceedings of the CLEF 2023: Conference and Labs of the Evaluation Forum, Thessaloniki, Greece. Available online: https://ceur-ws.org/Vol-3497/paper-148.pdf.
22. Miyaguchi, K., Takayama, M., Yamaguchi, Y., Ozasa, S., and Hirayama, H. Self-Supervised Learning and Distance Metric Ensemble for SnakeCLEF2024. CLEF2024 Working Notes, CEUR Workshop Proceedings. 2024, in press.
23. A Survey on Image Data Augmentation for Deep Learning10.1186/s40537-019-0197-0 ↗
24. Hu, X., Wang, C., Zhang, J., Wang, L., and Huang, K. (2020, January 6–10). RGB Channel Perturbation for Data Augmentation. Proceedings of the 2020 IEEE International Conference on Multimedia and Expo (ICME), London, UK.
25. Random Erasing Data Augmentation
26. Jaiswal, A., Babu, A.R., Zadeh, M.Z., Banerjee, D., and Makedon, F. (2021). A Survey on Contrastive Self-Supervised Learning. Technologies, 9.10.3390/technologies9010002 ↗
27. Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. arXiv.
28. Attention Is All You Need
29. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 20–25). Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/ICCV48922.2021.00986 ↗
30. A Survey on Vision Transformer10.1109/TPAMI.2022.3152247 ↗
31. Ioffe, S., and Szegedy, C. (2015, January 6–11). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning (ICML), Lile, France. Available online: https://proceedings.mlr.press/v37/ioffe15.html.
32. Supervised Contrastive Learning
33. Loshchilov, I., and Hutter, F. (2017). Decoupled Weight Decay Regularization. arXiv.
34. Loshchilov, I., and Hutter, F. (2017). SGDR: Stochastic Gradient Descent with Warm Restarts. arXiv.