{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-inaturalist-species-classification-and","title":"The iNaturalist Species Classification and Detection Dataset","arxiv_id":"1707.06642","date":"2017-07-20","proceeding":"CVPR 2018 6","authors":["Grant Van Horn","Oisin Mac Aodha","Yang song","Yin Cui","Chen Sun","Alex Shepard","Hartwig Adam","Pietro Perona","Serge Belongie"],"abstract":"Existing image classification datasets used in computer vision tend to have a\nuniform distribution of images across object categories. In contrast, the\nnatural world is heavily imbalanced, as some species are more abundant and\neasier to photograph than others. To encourage further progress in challenging\nreal world conditions we present the iNaturalist species classification and\ndetection dataset, consisting of 859,000 images from over 5,000 different\nspecies of plants and animals. It features visually similar species, captured\nin a wide variety of situations, from all over the world. Images were collected\nwith different camera types, have varying image quality, feature a large class\nimbalance, and have been verified by multiple citizen scientists. We discuss\nthe collection of the dataset and present extensive baseline experiments using\nstate-of-the-art computer vision classification and detection models. Results\nshow that current non-ensemble based methods achieve only 67% top one\nclassification accuracy, illustrating the difficulty of the dataset.\nSpecifically, we observe poor results for classes with small numbers of\ntraining examples suggesting more attention is needed in low-shot learning.","url_abs":"http://arxiv.org/abs/1707.06642v2","url_pdf":"http://arxiv.org/pdf/1707.06642v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/Puning97/AUTO-for-OOD-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/aioz-ai/multigraphfl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/deeplearning-wisc/cider","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/deeplearning-wisc/dice","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/deeplearning-wisc/gradnorm_ood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/deeplearning-wisc/knn-ood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/deeplearning-wisc/large_scale_ood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/deeplearning-wisc/npos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/deeplearning-wisc/react","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/deeplearning-wisc/snn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/haoqiwang/vim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/jimzai/mode-ood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/limchaos/likelihood-ood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/mapleleaf6/zode","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/tensorflow/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/tmlr-group/class_prior","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/tmlr-group/neglabel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/xixiliu95/gen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://gitlab.com/drti/neco","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-inaturalist-species-classification-and","repo_url":"https://github.com/MindSpore-scientific-2/code-5/tree/main/Datasets-Models-main","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[{"slug":"inaturalist","name":"iNaturalist","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-inaturalist","task":"Image Classification","dataset":"iNaturalist","model":"IncResNetV2 SE","rank_in_archive_order":14,"of":19,"metrics":{"Top 1 Accuracy":"67.3%","Top 5 Accuracy":"87.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"Inception-V3","rank_in_archive_order":54,"of":60,"metrics":{"Top-1 Accuracy":"60.20%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.06642","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}