@article{fdi:010083975,
  title = {{C}onfronting deep-learning and biodiversity challenges for automatic video-monitoring of marine ecosystems},
  author = {{V}illon, {S}. and {I}ovan, {C}orina and {M}angeas, {M}organ and {V}igliola, {L}aurent},
  editor = {},
  language = {{ENG}},
  abstract = {{W}ith the availability of low-cost and efficient digital cameras, ecologists can now survey the world's biodiversity through image sensors, especially in the previously rather inaccessible marine realm. {H}owever, the data rapidly accumulates, and ecologists face a data processing bottleneck. {W}hile computer vision has long been used as a tool to speed up image processing, it is only since the breakthrough of deep learning ({DL}) algorithms that the revolution in the automatic assessment of biodiversity by video recording can be considered. {H}owever, current applications of {DL} models to biodiversity monitoring do not consider some universal rules of biodiversity, especially rules on the distribution of species abundance, species rarity and ecosystem openness. {Y}et, these rules imply three issues for deep learning applications: the imbalance of long-tail datasets biases the training of {DL} models; scarce data greatly lessens the performances of {DL} models for classes with few data. {F}inally, the open-world issue implies that objects that are absent from the training dataset are incorrectly classified in the application dataset. {P}romising solutions to these issues are discussed, including data augmentation, data generation, cross-entropy modification, few-shot learning and open set recognition. {A}t a time when biodiversity faces the immense challenges of climate change and the {A}nthropocene defaunation, stronger collaboration between computer scientists and ecologists is urgently needed to unlock the automatic monitoring of biodiversity.},
  keywords = {ecology ; deep learning ; artificial {I}ntelligence ; ecosystem monitoring},
  booktitle = {},
  journal = {{S}ensors},
  volume = {22},
  numero = {2},
  pages = {497 [9 p.]},
  year = {2022},
  DOI = {10.3390/s22020497},
  URL = {https://www.documentation.ird.fr/hor/fdi:010083975},
}