{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T14:50:21Z","timestamp":1763391021789,"version":"3.45.0"},"reference-count":33,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"collaboration of the Biodiversity Foundation of the Ministry for Ecological Transition and the Demographic Challenge"},{"name":"European Union through the European Maritime, Fisheries and Aquaculture Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>The development of systems for the identification of elasmobranchs, including sharks and rays, is crucial for biodiversity conservation and fisheries management, as they represent one of the most threatened marine taxa. This challenge is constrained by data scarcity and the high morphological similarity among species, which limits the applicability of traditional supervised models trained on specific datasets. In this work, we propose an informed zero-shot learning approach that integrates external expert knowledge into the inference process, leveraging the multimodal CLIP framework. The methodology incorporates three main sources of knowledge: detailed text descriptions provided by specialists, schematic illustrations highlighting distinctive morphological traits, and the taxonomic hierarchy that organizes species at different levels. Based on these resources, we design a pipeline for prompt extraction and validation, taxonomy-aware classification strategies, and enriched embeddings through a prototype-guided attention mechanism. The results show significant improvements in CLIP\u2019s discriminative capacity in a complex problem characterized by high inter-class similarity and the absence of annotated examples, demonstrating the value of integrating domain knowledge into methodology development and providing a framework adaptable to other problems with similar constraints.<\/jats:p>","DOI":"10.3390\/make7040146","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T14:37:52Z","timestamp":1763131072000},"page":"146","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Elasmobranch Classification Informed by Domain Prior Knowledge"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2386-9611","authenticated-orcid":false,"given":"Ismael","family":"Bevi\u00e1-Ballesteros","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, University of Alicante, 03690 San Vicente del Raspeig, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8577-4104","authenticated-orcid":false,"given":"Mario","family":"Jerez-Tall\u00f3n","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, University of Alicante, 03690 San Vicente del Raspeig, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8006-0489","authenticated-orcid":false,"given":"Nieves","family":"Aranda-Garrido","sequence":"additional","affiliation":[{"name":"Marine Research Center of Santa Pola, University of Alicante, 03130 Santa Pola, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6245-5145","authenticated-orcid":false,"given":"Marcelo","family":"Saval-Calvo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, University of Alicante, 03690 San Vicente del Raspeig, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6221-4641","authenticated-orcid":false,"given":"Isabel","family":"Abel-Abell\u00e1n","sequence":"additional","affiliation":[{"name":"Marine Research Center of Santa Pola, University of Alicante, 03130 Santa Pola, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0938-6344","authenticated-orcid":false,"given":"Andr\u00e9s","family":"Fuster-Guill\u00f3","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, University of Alicante, 03690 San Vicente del Raspeig, Spain"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"ref_1","unstructured":"Jabado, R.W., Morata, A.Z.A., Bennett, R.H., Finucci, B., Ellis, J.R., Fowler, S.L., Grant, M.I., Barbosa Martins, A.P., and Sinclair, S.L. (2024). The Global Status of Sharks, Rays, and Chimaeras, IUCN Species Survival Commission (SSC), Shark Specialist Group."},{"key":"ref_2","unstructured":"Pozo-Montoro, M., Arroyo, E., Abel, I., Bas G\u00f3mez, A., Clemente Navarro, P., Cort\u00e9s, E., Esteban, A., Garc\u00eda-Charton, J.A., L\u00f3pez Castej\u00f3n, F., and Ortolano, A. Important Shark and Ray Areas (ISRAs) en el SE ib\u00e9rico, una declaraci\u00f3n necesaria. Proceedings of the XV Reuni\u00f3n del Foro Cient\u00edfico Sobre la Pesca Espa\u00f1ola en el Mediterr\u00e1neo."},{"key":"ref_3","unstructured":"Jabado, R.W., Garc\u00eda-Rodr\u00edguez, E., Kyne, P.M., Charles, R., Armstrong, A.H., Bortoluzzi, J., Mouton, T.L., Gonzalez-Pestana, A., Battle-Morera, A., and Rohner, C. (2023). Mediterranean and Black Seas: A Regional Compendium of Important Shark and Ray Areas, IUCN SSC Shark Specialist Group. Technical report."},{"key":"ref_4","first-page":"4051","article-title":"A Review of Generalized Zero-Shot Learning Methods","volume":"45","author":"Pourpanah","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_5","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021). Learning Transferable Visual Models From Natural Language Supervision. arXiv."},{"key":"ref_6","first-page":"614","article-title":"Informed Machine Learning\u2014A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems","volume":"35","author":"Mayer","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"101673","DOI":"10.1016\/j.ecoinf.2022.101673","article-title":"Shark detection and classification with machine learning","volume":"69","author":"Jenrette","year":"2022","journal-title":"Ecol. Inform."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"102499","DOI":"10.1016\/j.ecoinf.2024.102499","article-title":"Toward an artificial intelligence-assisted counting of sharks on baited video","volume":"80","author":"Villon","year":"2024","journal-title":"Ecol. Inform."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Clark, J., Lalgudi, C., Leone, M., Meribe, J., Madrigal-Mora, S., and Espinoza, M. (2025). Deep Learning for Automated Shark Detection and Biometrics Without Keypoints. Computer Vision\u2014ECCV 2024 Workshops, Springer.","DOI":"10.1007\/978-3-031-92387-6_7"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Purcell, C., Walsh, A., Colefax, A., and Butcher, P. (2022). Assessing the ability of deep learning techniques to perform real-time identification of shark species in live streaming video from drones. Front. Mar. Sci., 9.","DOI":"10.3389\/fmars.2022.981897"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"102036","DOI":"10.1016\/j.ecoinf.2023.102036","article-title":"Re-identification of fish individuals of undulate skate via deep learning within a few-shot context","volume":"75","author":"Blanquero","year":"2023","journal-title":"Ecol. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Garcia-D\u2019Urso, N.E., Galan-Cuenca, A., Climent-P\u00e9rez, P., Saval-Calvo, M., Azorin-Lopez, J., and Fuster-Guillo, A. (2022, January 18\u201323). Efficient instance segmentation using deep learning for species identification in fish markets. Proceedings of the 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy.","DOI":"10.1109\/IJCNN55064.2022.9892945"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e1770","DOI":"10.7717\/peerj-cs.1770","article-title":"Simultaneous, vision-based fish instance segmentation, species classification and size regression","volume":"10","year":"2024","journal-title":"PeerJ Comput. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Lu, J., Song, Z., Zhao, S., Li, D., and Zhao, R. (2024). A Metric-Based Few-Shot Learning Method for Fish Species Identification with Limited Samples. Animals, 14.","DOI":"10.3390\/ani14050755"},{"key":"ref_15","first-page":"66","article-title":"Comparative Study of Deep Learning Approaches for Fish Origin Classification","volume":"Volume 16008","author":"Rojas","year":"2025","journal-title":"Advances in Computational Intelligence. IWANN 2025"},{"key":"ref_16","unstructured":"Menon, S., and Vondrick, C. (2022). Visual Classification via Description from Large Language Models. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., and Hassner, T. Tip-Adapter: Training-Free Adaption of CLIP for Few-Shot Classification. Proceedings of the Computer Vision\u2014ECCV 2022.","DOI":"10.1007\/978-3-031-19775-8"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Guo, Z., Zhang, R., Qiu, L., Ma, X., Miao, X., He, X., and Cui, B. (2022). CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention. arXiv.","DOI":"10.1609\/aaai.v37i1.25152"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhuang, J., Hu, J., Mu, L., Hu, R., Liang, X., Ye, J., and Hu, H. (2024). FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance. Computer Vision\u2014ECCV 2024, Springer.","DOI":"10.1007\/978-3-031-72684-2_14"},{"key":"ref_20","unstructured":"Li, Y., Liang, F., Zhao, L., Cui, Y., Ouyang, W., Shao, J., Yu, F., and Yan, J. (2022). Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm. arXiv."},{"key":"ref_21","unstructured":"Yuksekgonul, M., Bianchi, F., Kalluri, P., Jurafsky, D., and Zou, J. (2023). When and why vision-language models behave like bags-of-words, and what to do about it?. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Praveena, K., Anandhi, R., Gupta, S., Jain, A., Kumar, A., and Saud, A.M. (2024, January 22\u201323). Application of Zero-Shot Learning in Computer Vision for Biodiversity Conservation through Species Identification and Tracking. Proceedings of the 2024 International Conference on Trends in Quantum Computing and Emerging Business Technologies, Pune, India.","DOI":"10.1109\/TQCEBT59414.2024.10545030"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., and Harmeling, S. (2009, January 20\u201325). Learning to detect unseen object classes by between-class attribute transfer. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPRW.2009.5206594"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lampert, C.H., Schiele, B., and Akata, Z. (2020). Zero-Shot Learning\u2014A Comprehensive Evaluation of the Good, the Bad and the Ugly. arXiv.","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez, A.C., D\u2019Aronco, S., Daudt, R.C., Wegner, J.D., and Schindler, K. (2024, January 3\u20138). Recognition of Unseen Bird Species by Learning from Field Guides. Proceedings of the WACV, Waikoloa, HI, USA.","DOI":"10.1109\/WACV57701.2024.00176"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Stevens, S., Wu, J., Thompson, M.J., Campolongo, E.G., Song, C.H., Carlyn, D.E., Dong, L., Dahdul, W.M., Stewart, C., and Berger-Wolf, T. (2024, January 16\u201322). BioCLIP: A Vision Foundation Model for the Tree of Life. Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01836"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1280","DOI":"10.1134\/S1061830923600855","article-title":"Automatic Segmentation by the Method of Interval Fusion with Preference Aggregation When Recognizing Weld Defects","volume":"59","author":"Muravyov","year":"2023","journal-title":"Russ. J. Nondestruct. Test."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"114969","DOI":"10.1016\/j.measurement.2024.114969","article-title":"Method of Interval Fusion with Preference Aggregation in Brightness Thresholds Selection for Automatic Weld Surface Defects Recognition","volume":"236","author":"Muravyov","year":"2024","journal-title":"Measurement"},{"key":"ref_29","unstructured":"Snell, J., Swersky, K., and Zemel, R.S. (2017). Prototypical Networks for Few-shot Learning. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Sui, D., Chen, Y., Mao, B., Qiu, D., Liu, K., and Zhao, J. (2020). Knowledge Guided Metric Learning for Few-Shot Text Classification. arXiv.","DOI":"10.18653\/v1\/2021.naacl-main.261"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhang, N., Xie, X., Deng, S., Yao, Y., Tan, C., Huang, F., Si, L., and Chen, H. (2022, January 25\u201329). KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction. Proceedings of the Proceedings of the ACM Web Conference 2022, Lyon, France.","DOI":"10.1145\/3485447.3511998"},{"key":"ref_32","unstructured":"Moloch (2025, October 01). iNaturalist Observation: Prionace Glauca (Blue Shark). Available online: https:\/\/www.inaturalist.org\/observations\/8641690."},{"key":"ref_33","unstructured":"Arroyo, E., Canales C\u00e1ceres, R.M., Abel, I., and Gim\u00e9nez-Casalduero, F. (2021). Tiburones y Rayas de la Regi\u00f3n de Murcia, Proyecto TIBURCIA, Fondo Europeo Mar\u00edtimo y de Pesca."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/4\/146\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T14:46:18Z","timestamp":1763390778000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/4\/146"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":33,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["make7040146"],"URL":"https:\/\/doi.org\/10.3390\/make7040146","relation":{},"ISSN":["2504-4990"],"issn-type":[{"type":"electronic","value":"2504-4990"}],"subject":[],"published":{"date-parts":[[2025,11,14]]}}}