Abstract
This paper presents an approach to image segmentation and classification algorithm where the dataset has only few images labelled, done intentionally. The method tries to classify only the few instances with enough quality in the image, the KeyFish. In order to not being punished with wrong false positives, it must learn the examples but not the context. The application is intended for wholesale fish markets. Due to the depth and occlusions of the fish tray, the camera can only visualize a small fraction of the total instances. The main goal is to predict in the best possible quality the few fish seen, regardless of other occurrences. Tests have been made over Yolact++ architecture and the proposed method, with an increase in precision from 85.97% to 89.69% in bounding box and 74.03% to 81.42% in detection of the mask for a 50% overlap limit.
This work was supported by the Spanish State Research Agency (AEI) under grant PID2020-119144RB-I00 funded by MCIN/AEI/10.13039/501100011033.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Deepfish project (2021). https://deepfish.dtic.ua.es/
Ao, J., Ehinger, K.A., Ke, Q.: Image amodal completion: a survey (2022). https://doi.org/10.48550/ARXIV.2207.02062
Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: YOLACT: real-time instance segmentation. In: ICCV (2019)
Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: YOLACT++: better real-time instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (2020)
Ángeles Cerón, J.C., Chang, L., Ruiz, G.O., Ali, S.: Assessing YOLACT++ for real time and robust instance segmentation of medical instruments in endoscopic procedures, pp. 1824–1827 (2021). https://doi.org/10.1109/EMBC46164.2021.9629914
Climent-Pérez, P., Galán-Cuenca, A., García-d’Urso, N.E., Saval-Calvo, M., Azorin-Lopez, J., Fuster-Guillo, A.: Automatic fish size estimation from uncalibrated fish market images using computer vision and deep learning. In: García Bringas, P., et al. (eds.) SOCO 2022. LNNS, vol. 531, pp. 319–329. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-18050-7_31
Cour, T., Sapp, B., Jordan, C., Taskar, B.: Learning from ambiguously labeled images. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 919–926 (2009). https://doi.org/10.1109/CVPR.2009.5206667
Cuenca, A.G., Sánchez, P.P., Guilló, A.F., López, J.A.: Deepfish2 dataset (2022). https://doi.org/10.5281/zenodo.7108754
Durand, T., Mehrasa, N., Mori, G.: Learning a deep ConvNet for multi-label classification with partial labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
FAO: The State of Mediterranean and Black Sea Fisheries 2020. FAO (2020). https://doi.org/10.4060/cb2429en
Garcia-D’Urso, N.E., Galan-Cuenca, A., Climent-Pérez, P., Saval-Calvo, M., Azorin-Lopez, J., Fuster-Guillo, A.: Efficient instance segmentation using deep learning for species identification in fish markets. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2022). https://doi.org/10.1109/IJCNN55064.2022.9892945
Huynh, D., Elhamifar, E.: Interactive multi-label CNN learning with partial labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Qi, L., Jiang, L., Liu, S., Shen, X., Jia, J.: Amodal instance segmentation with KINS dataset. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3009–3018 (2019). https://doi.org/10.1109/CVPR.2019.00313
Xu, X., Shimada, A., Nagahara, H., Taniguchi, R.i., He, L.: Image annotation with incomplete labelling by modelling image specific structured loss. IEEJ Trans. Electr. Electron. Eng. (2016). https://doi.org/10.1002/tee.22190
Acknowledgements
This research has made use of the DGX-A100 cluster at the University of Alicante, funded by the Conselleria d’Innovació, Universitats, Ciència i Societat Digital of the Generalitat Valenciana and the European Union through the project entitled ”Investigación en técnicas de aprendizaje profundo a grandes volúmenes de datos multimodales” (IDIFEDER/2020/003). This work has also been developed with the support of valgrAI - Valencian Graduate School and Research Network of Artificial Intelligence and the Generalitat Valenciana, and co-funded by the European Union. This work is part of the DeepFish2 project, which has been funded by Fundación Biodiversidad. Ministerio para la Transición Ecológica y el Reto Demográfico. Programa PLEAMAR, and has also been co-financed by the Fondo Europeo Marítimo y de Pesca, FEMP. Additionally, this work has been partially funded by the Ministerio de Ciencia, Innovación y Universidades through the project TIN2017-89069-R of the RETOS supported by Feder funds.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Galán-Cuenca, A., García-d’Urso, N., Climent-Pérez, P., Fuster-Guillo, A., Azorin-Lopez, J. (2023). A Modified Loss Function Approach for Instance Segmentation Improvement and Application in Fish Markets. In: García Bringas, P., et al. 18th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2023). SOCO 2023. Lecture Notes in Networks and Systems, vol 750. Springer, Cham. https://doi.org/10.1007/978-3-031-42536-3_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-42536-3_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42535-6
Online ISBN: 978-3-031-42536-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)