Aqua Vision: Few-Shot Learning Based Efficient Fish Identification in Challenging Aquatic Habitats

Aquatic ecosystems play a vital role in marine biodiversity and coastal protection, yet monitoring these habitats remains a significant challenge due to the scarcity of labeled data for training robust detection models. Traditional approaches often rely on extensive labeled datasets, which are costly and time-consuming to obtain, leading to a critical research gap in effective fish detection methodologies. This study introduces an innovative approach to fish detection by leveraging few-shot learning and pseudo-labeling techniques. We employ SimCLR, a contrastive learning framework, to pre-train a ResNet50-based encoder on unlabeled Deep Fish images, thereby extracting robust feature representations. These features are then utilized to train a Faster R-CNN object detection model using a limited set of labeled sea grass images. To further enhance the model’s performance, we incorporate pseudo-labeling, a semi-supervised learning technique that generates additional training data from unlabeled images based on a confidence threshold. Our methodology demonstrates significant improvements in fish detection accuracy. The final model achieves an average precision of 0.8167 and recall of 0.7967, outperforming other state-of-the-art models such as YOLOv5 and RetinaNet. These results highlight the effectiveness of combining few-shot learning with pseudo-labeling in addressing the challenge of limited labeled data, paving the way for more efficient and accurate marine ecosystem monitoring.

Fish detection, Few-shot learning, Pseudo- labeling, SimCLR

1. Ahmed, R., & Tamim, M. T. R. (2025). Marine and Coastal Environments: Challenges, Impacts, and Strategies for a Sustainable Future. International Journal of Science Education and Science, 2(1), 53-60. [Google Scholar] [Crossref]

2. Douglas, J., Niner, H., & Garrard, S. (2024). Impacts of marine plastic pollution on seagrass meadows and ecosystem services in Southeast Asia. Journal of Marine Science and Engineering, 12(12), 2314. [Google Scholar] [Crossref]

3. Schmid, B., & Schöb, C. (2022). Biodiversity and ecosystem services in managed ecosystems. In The ecological and societal consequences of biodiversity loss (pp. 213-231). ISTE Ltd and John Wiley & Sons, Inc, London. [Google Scholar] [Crossref]

4. Hong, J. H., Semprucci, F., Jeong, R., Kim, K., Lee, S., Jeon, D., ... & Lee, W. (2020). Meiobenthic nematodes in the assessment of the relative impact of human activities on coastal marine ecosystem. Environmental Monitoring and Assessment, 192(2), 81.. [Google Scholar] [Crossref]

5. Lopez-Vazquez, V., Lopez-Guede, J. M., Marini, S., Fanelli, E., Johnsen, E., & Aguzzi, J. (2020). Video image enhancement and machine learning pipeline for underwater animal detection and classification at cabled observatories. Sensors, 20(3), 726. [Google Scholar] [Crossref]

6. Jalal, A., Salman, A., Mian, A., Shortis, M., & Shafait, F. (2020). Fish detection and species classification in underwater environments using deep learning with temporal information. Ecological Informatics, 57, 101088. [Google Scholar] [Crossref]

7. Meena, T., Vijaya, J., & Harsha, B. (2025, February). Swin Transformers for Remote Sensing SAR Image Classification. In 2025 IEEE International Conference on Emerging Technologies and Applications (MPSec ICETA) (pp. 1-6). IEEE. [Google Scholar] [Crossref]

8. Vijaya, J., Gopu, A., Suman, P., & Chaitanya, S. (2024, May). Revolutionising Image Enhancement Leveraging Power OF CNN’S. In 2024 3rd International Conference on Artificial Intelligence For Internet of Things (AIIoT) (pp. 1-6). IEEE. [Google Scholar] [Crossref]

9. Yassir, A., Andaloussi, S. J., Ouchetto, O., Mamza, K., & Serghini, M. (2023). Acoustic fish species identification using deep learning and machine learning algorithms: A systematic review. Fisheries Research, 266, 106790. [Google Scholar] [Crossref]

10. Fu, C., Liu, R., Fan, X., Chen, P., Fu, H., Yuan, W., ... & Luo, Z. (2023). Rethinking general underwater object detection: Datasets, challenges, and solutions. Neurocomputing, 517, 243-256. [Google Scholar] [Crossref]

11. Er, M. J., Chen, J., Zhang, Y., & Gao, W. (2023). Research challenges, recent advances, and popular datasets in deep learning-based underwater marine object detection: A review. Sensors, 23(4), 1990. [Google Scholar] [Crossref]

12. Li, J., Yang, W., Qiao, S., Gu, Z., Zheng, B., & Zheng, H. (2024). Self-supervised marine organism detection from underwater images. IEEE Journal of Oceanic Engineering. [Google Scholar] [Crossref]

13. Chungath, T. T., Nambiar, A. M., & Mittal, A. (2023). Transfer learning and few-shot learning based deep neural network models for underwater sonar image classification with a few samples. IEEE Journal of Oceanic Engineering, 49(1), 294-310. [Google Scholar] [Crossref]

14. Sohn, K., Berthelot, D., Carlini, N., Zhang, Z., Zhang, H., Raffel, C. A., ... & Li, C. L. (2020). Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems, 33, 596-608. [Google Scholar] [Crossref]

15. Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020, November). A simple framework for contrastive learning of visual representations. In International conference on machine learning (pp. 1597-1607). PmLR. [Google Scholar] [Crossref]

16. Snell, J., Swersky, K., & Zemel, R. (2017). Prototypical networks for few-shot learning. Advances in neural information processing systems, 30. [Google Scholar] [Crossref]

17. Tarvainen, A., & Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, 30. [Google Scholar] [Crossref]

18. Li, L., Shi, G., & Jiang, T. (2023). Fish detection method based on improved YOLOv5. Aquaculture International, 31(5), 2513-2530. [Google Scholar] [Crossref]

19. Shen, Z., & Nguyen, C. (2020, November). Temporal 3D RetinaNet for fish detection. In 2020 Digital Image Computing: Techniques and Applications (DICTA) (pp. 1-5). IEEE. [Google Scholar] [Crossref]

20. Vyshnav, K., Sooryanarayanan, R., & Madhav, T. V. (2024, April). Analysis of Underwater Coral Reef Health Using Neural Networks. In OCEANS 2024-Singapore (pp. 01-06). IEEE. [Google Scholar] [Crossref]

21. Chowdhury, A., Jahan, M., Kaisar, S., Khoda, M. E., Rajin, S. A. K., & Naha, R. (2024). Coral Reef Surveillance with Machine Learning: A Review of Datasets, Techniques, and Challenges. Electronics, 13(24), 5027. [Google Scholar] [Crossref]

22. https://homepages.inf.ed.ac.uk/rbf/fish4knowledge/ [Google Scholar] [Crossref]

23. https://www.kaggle.com/datasets/lywang777/urpc2020 [Google Scholar] [Crossref]

24. https://datasetninja.com/deep-fish [Google Scholar] [Crossref]

25. Elmezain, M., Saoud, L. S., Sultan, A., Heshmat, M., Seneviratne, L., & Hussain, I. (2025). Advancing underwater vision: a survey of deep learning models for underwater object recognition and tracking. IEEE Access. [Google Scholar] [Crossref]

26. Zhang, F., Hu, J., & Sun, Y. (2025). Underwater fish image recognition based on knowledge graphs and semi-supervised learning feature enhancement. Scientific Reports. [Google Scholar] [Crossref]

27. Dalla Serra, F., Jacenków, G., Deligianni, F., Dalton, J., & O’Neil, A. Q. (2022, July). Improving Image Representations via MoCo Pre-training for Multimodal CXR Classification. In Annual Conference on Medical Image Understanding and Analysis (pp. 623-635). Cham: Springer International Publishing. [Google Scholar] [Crossref]

28. Niizumi, D., Takeuchi, D., Ohishi, Y., Harada, N., & Kashino, K. (2021, July). Byol for audio: Self-supervised learning for general-purpose audio representation. In 2021 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE. [Google Scholar] [Crossref]

29. Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., & Raffel, C. A. (2019). Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems, 32. [Google Scholar] [Crossref]

30. Fallah, A., Mokhtari, A., & Ozdaglar, A. (2020, June). On the convergence theory of gradient-based model-agnostic meta-learning algorithms. In International Conference on Artificial Intelligence and Statistics (pp. 1082-1092). PMLR. [Google Scholar] [Crossref]

31. Lu, J., Zhang, S., Zhao, S., Li, D., & Zhao, R. (2024). A metric-based few-shot learning method for fish species identification with limited samples. Animals, 14(5), 755. [Google Scholar] [Crossref]

32. https://alzayats.github.io/DeepFish/ [Google Scholar] [Crossref]

33. https://github.com/globalwetlands/luderick-seagrass [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet