mlsanityData to 7 Oct 2026

The iWildCam 2021 Competition Dataset

arXiv 2105.03494 ↗First posted 7 May 2021cs.CVcited by 77

Not on the map. Why?

Abstract (arXiv)

Camera traps enable the automatic collection of large quantities of image data. Ecologists use camera traps to monitor animal populations all over the world. In order to estimate the abundance of a species from camera trap data, ecologists need to know not just which species were seen, but also how many individuals of each species were seen. Object detection techniques can be used to find the number of individuals in each image. However, since camera traps collect images in motion-triggered bursts, simply adding up the number of detections over all frames is likely to lead to an incorrect estimate. Overcoming these obstacles may require incorporating spatio-temporal reasoning or individual re-identification in addition to traditional species detection and classification. We have prepared a challenge where the training data and test data are from different cameras spread across the globe. The set of species seen in each camera overlap, but are not identical. The challenge is to classify species and count individual animals across sequences in the test cameras.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). Builds on 20 of its 42 references that are in the map. First posted on arXiv 7 May 2021.

Builds on

20 of 42 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  4. 2018Recognition in Terra Incognitacited by 655
  5. 2019Presence-Only Geographical Priors for Fine-Grained Image Classificationcited by 109
  6. 2020The iWildCam 2020 Competition Datasetcited by 86
  7. 2019Efficient Pipeline for Camera Trap Image Reviewcited by 79
  8. 2018Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Datacited by 45
  9. 2019Context R-CNN: Long Term Temporal Context for Per-Camera Object Detectioncited by 45
  10. 2019Geo-Aware Networks for Fine-Grained Recognitioncited by 44
  11. 2019A deep active learning system for species identification and counting in camera trap imagescited by 44
  12. 2019Synthetic Examples Improve Generalization for Rare Classescited by 35
8 more
  1. 2021Perspectives on individual animal identification from biology and computer visioncited by 31
  2. 2016Towards Automatic Wild Animal Monitoring: Identification of Animal Species in Camera-trap Images using Very Deep Convolutional Neural Networkscited by 28
  3. 2018Deep Learning Object Detection Methods for Ecological Camera Trap Datacited by 16
  4. 2019The iWildCam 2018 Challenge Datasetcited by 14
  5. 2021The surprising impact of mask-head architecture on novel class segmentationcited by 13
  6. 2019The iWildCam 2019 Challenge Datasetcited by 6
  7. 2017Camera-trap images segmentation using multi-layer robust principal component analysiscited by 5
  8. 2017Automatically identifying, counting, and describing wild animals in camera-trap images with deep learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 12; 2023: 17; 2024: 23; 2025: 14; 2026: 5.

77 papers.

Sort:

By area:

  1. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  2. 2021Robust fine-tuning of zero-shot modelscited by 785
  3. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  4. 2023BioCLIP: A Vision Foundation Model for the Tree of Lifecited by 159
  5. 2022Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understandingcited by 102
  6. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  7. 2022Probable Domain Generalization via Quantile Risk Minimizationcited by 66
  8. 2024ViTamin: Designing Scalable Vision Models in the Vision-Language Eracited by 39
  9. 2023Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalizationcited by 31
  10. 2024On the Out-Of-Distribution Generalization of Multimodal Large Language Modelscited by 30
  11. 2022The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Countingcited by 24
  12. 2022Bugs in the Data: How ImageNet Misrepresents Biodiversitycited by 24
38 more
  1. 2023Out-of-Domain Robustness via Targeted Augmentationscited by 24
  2. 2024Adapting to Distribution Shift by Visual Domain Prompt Generationcited by 23
  3. 2023How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigationcited by 22
  4. 2024PanAf20K: A Large Video Dataset for Wild Ape Detection and Behaviour Recognitioncited by 22
  5. 2021Species Distribution Modeling for Machine Learning Practitioners: A Reviewcited by 21
  6. 2022Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergycited by 20
  7. 2023LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learningcited by 20
  8. 2024A Survey on Evaluation of Out-of-Distribution Generalizationcited by 20
  9. 2022Localized Adversarial Domain Generalizationcited by 19
  10. 2022lo-fi: distributed fine-tuning without communicationcited by 19
  11. 2024Active Data Curation Effectively Distills Large-Scale Multimodal Modelscited by 19
  12. 2022Rethinking Few-Shot Object Detection on a Multi-Domain Benchmarkcited by 17
  13. 2023Domain Generalization via Rationale Invariancecited by 16
  14. 2024Probabilistic Language-Image Pre-Trainingcited by 16
  15. 2025Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptationcited by 14
  16. 2023FedCiR: Client-Invariant Representation Learning for Federated Non-IID Featurescited by 12
  17. 2023CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysiscited by 12
  18. 2024Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environmentcited by 12
  19. 2023Contextual Vision Transformers for Robust Representation Learningcited by 10
  20. 2023Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separationcited by 8
  21. 2024Controlled Training Data Generation with Diffusion Modelscited by 8
  22. 2023Text Descriptions are Compressive and Invariant Representations for Visual Learningcited by 7
  23. 2023Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Datacited by 7
  24. 2024Insect Identification in the Wild: The AMI Datasetcited by 6
  25. 2024Diffusion Curriculum: Synthetic-to-Real Data Curriculum via Image-Guided Diffusioncited by 6
  26. 2024Cross-domain Multi-modal Few-shot Object Detection via Rich Textcited by 5
  27. 2024Sample- and Parameter-Efficient Auto-Regressive Image Modelscited by 5
  28. 2025The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognitioncited by 5
  29. 2024A Causal Inspired Early-Branching Structure for Domain Generalizationcited by 4
  30. 2024DivShift: Exploring Domain-Specific Distribution Shifts in Large-Scale, Volunteer-Collected Biodiversity Datasetscited by 4
  31. 2025Unified modality separation: A vision-language framework for unsupervised domain adaptationcited by 4
  32. 2025Weak-to-Strong Generalization under Distribution Shiftscited by 4
  33. 2021Domain Adaptation for Rare Classes Augmented with Synthetic Samplescited by 3
  34. 2021Domain-Aware Continual Zero-Shot Learningcited by 3
  35. 2022Bag of Tricks for Long-Tail Visual Recognition of Animal Species in Camera-Trap Imagescited by 3
  36. 2024AutoFT: Learning an Objective for Robust Fine-Tuningcited by 3
  37. 2024Robust Adaptation of Foundation Models with Black-Box Visual Promptingcited by 3
  38. 2024Deep learning-based ecological analysis of camera trap images is impacted by training data quality and quantitycited by 3

50 most cited of 77 All 77 (JSON)