Overview of the SnakeCLEF 2020: AutomaticSnake Species Identification Challenge

Building a robust and accurate AI-driven system for automatic snake species identification is an important goal for biodiversity and global health. As the existence of such a system can potentially help to lower deaths and disabilities caused by snakebites, we have prepared SnakeCLEF2020: Automatic Snake Species Identification Challenge, which provides an evaluation platform and labeled data (including geographical information) for biodiversity and health research purposes. SnakeCLEF 2020 was designed to provide an evaluation platform that can help track the performance of end-to-end AI-driven snake species recognition systems. We have collected 287,632 images of 783 snake species from 145 countries. Here we report 1) a description of the provided data, 2) evaluation methodology and principles, 3) an overview of the systems submitted by the participating teams, and 4) a discussion of the obtained results.

[1]  Leslie V. Boyer,et al.  Non-Native (Exotic) Snake Envenomations in the U.S., 2005–2011 , 2014, Toxins.

[2]  Jessica A. Lyons,et al.  Serpent's source: Determining the source and geographic origin of traded python skins using isotopic and elemental markers , 2017 .

[3]  Patrick Mäder,et al.  Recommending plant taxa for supporting on-site species identification , 2018, BMC Bioinformatics.

[4]  Philip W. Bateman,et al.  What snake is that? Common Australian snake species are frequently misidentified or unidentified , 2020 .

[5]  Stefan Kahl,et al.  Overview of LifeCLEF 2020: A System-Oriented Evaluation of Automated Species Identification and Species Distribution Prediction , 2020, CLEF.

[6]  Patrick Mäder,et al.  Plant species classification using flower images—A comparative study of local feature representations , 2017, PloS one.

[7]  R. Badlishah Ahmad,et al.  Snake species identification by using natural language processing , 2019, Indonesian Journal of Electrical Engineering and Computer Science.

[8]  J. Chippaux,et al.  [Guidelines for the production, control and regulation of snake antivenom immunoglobulins]. , 2010, Biologie aujourd'hui.

[9]  R. Galli,et al.  Misidentification of copperhead and cottonmouth snakes following snakebites* , 2018, Clinical toxicology.

[10]  Christoph M. Friedrich,et al.  Variations on Branding with Text Occurrence for Optimized Body Parts Classification , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[11]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[12]  Jiri Matas,et al.  Recognition of the Amazonian flora by InceptionNetworks with Test-time Class Prior Estimation , 2019, CLEF.

[13]  Pranalini Joshi,et al.  A Survey on Snake Species Identification using Image Processing Technique , 2018, International Journal of Computer Applications.

[14]  Hongyi Zhang,et al.  mixup: Beyond Empirical Risk Minimization , 2017, ICLR.

[15]  David J. Williams,et al.  Strategy for a globally coordinated response to a priority neglected tropical disease: Snakebite envenoming , 2019, PLoS neglected tropical diseases.

[16]  Pietro Perona,et al.  Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Johannes Rückert,et al.  Combination of Image and Location Information for Snake Species Identification using Object Detection and EfficientNets , 2020, CLEF.

[18]  Moorthy Gokula Krishnan,et al.  Impact of Pretrained Networks For Snake Species Classification , 2020, CLEF.

[19]  André Calero Valdez,et al.  Towards Interactive Recommender Systems with the Doctor-in-the-Loop , 2016, MuC.

[20]  Patrick Mäder,et al.  Acquiring and preprocessing leaf images for automated plant identification: understanding the tradeoff between effort and information gain , 2017, Plant Methods.

[21]  Marco Willi,et al.  Identifying animal species in camera trap images using deep learning and citizen science , 2018, Methods in Ecology and Evolution.

[22]  Yang Song,et al.  The iNaturalist Species Classification and Detection Dataset , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[23]  Carlos Zambrana-Torrelio,et al.  Forty-four years of global trade in CITES-listed snakes: Trends and implications for conservation and public health , 2020 .

[24]  Jiri Matas,et al.  Plant Recognition by Inception Networks with Test-time Class Prior Estimation , 2018, CLEF.

[25]  Marcel Salathé,et al.  Snakebite and snake identification: empowering neglected communities and health-care providers with AI. , 2019, The Lancet. Digital health.

[26]  Uetz Peter,et al.  The Reptile Database , 1995 .

[27]  R. Badlishah Ahmad,et al.  Image Classification for Snake Species Using Machine Learning Techniques , 2016 .

[28]  Scott E. Henke,et al.  Efficacy of an Online Native Snake Identification Search Engine for Public Use , 2019 .

[29]  Margaret Kosmala,et al.  Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning , 2017, Proceedings of the National Academy of Sciences.

[30]  Peter Uetz,et al.  The global distribution of tetrapods reveals a need for targeted reptile conservation , 2017, Nature Ecology & Evolution.

[31]  Lucas Beyer,et al.  Big Transfer (BiT): General Visual Representation Learning , 2020, ECCV.

[32]  Patrick Mäder,et al.  Automated plant species identification—Trends and future directions , 2018, PLoS Comput. Biol..

[33]  Isabelle Bolon,et al.  Identifying the snake: First scoping review on practices of communities and healthcare providers confronted with snakebite across the world , 2020, PloS one.

[34]  J. Menzies,et al.  Alien Reptiles and Amphibians: A Scientific Compendium and Analysis. , 2009 .

[35]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[36]  Herbert Desel,et al.  Bites and stings by exotic pets in Europe: An 11 year analysis of 404 cases from Northeastern Germany and Southeastern France , 2009, Clinical toxicology.

[37]  M. Cabrera-Pérez,et al.  The management and control of the California kingsnake in Gran Canaria (Canary Islands): project LIFE+ Lampropeltis. , 2012 .

[38]  Patrick Mäder,et al.  Flowers, leaves or both? How to obtain suitable images for automated plant identification , 2019, Plant Methods.

[39]  F. Kraus,et al.  Alien reptiles and amphibians : a scientific compendium and analysis , 2009 .

[40]  Miroslav Valan,et al.  Mastering Large Scale Multi-label Image Recognition with high efficiency overCamera trap images , 2020, ArXiv.