# Danish Fungi 2020 -- Not Just Another Image Recognition Dataset

arXiv: https://arxiv.org/abs/2103.10107 · HTML: https://mlsanity.com/paper/2103.10107/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 63 references that are in the map.
- First posted on arXiv 18 Mar 2021.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Are we done with ImageNet?](https://mlsanity.com/paper/2006.07159/) (2020)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [Evaluating model calibration in classification](https://mlsanity.com/paper/1902.06977/) (2019)
- [Interpretable Convolutional Neural Networks](https://mlsanity.com/paper/1710.00935/) (2017)
- [Presence-Only Geographical Priors for Fine-Grained Image Classification](https://mlsanity.com/paper/1906.05272/) (2019)
- [Unsupervised Part-Based Disentangling of Object Shape and Appearance](https://mlsanity.com/paper/1903.06946/) (2019)
- [Bird Species Categorization Using Pose Normalized Deep Convolutional Nets](https://mlsanity.com/paper/1406.2952/) (2014)
- [The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition](https://mlsanity.com/paper/1511.06789/) (2015)
- [Few-Shot Learning with Localization in Realistic Settings](https://mlsanity.com/paper/1904.08502/) (2019)
- [Fine-grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach](https://mlsanity.com/paper/1709.02476/) (2017)
- [Improving CNN classifiers by estimating test-time priors](https://mlsanity.com/paper/1805.08235/) (2018)

## Built on by (most cited first, 27 of 27)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [BioCLIP: A Vision Foundation Model for the Tree of Life](https://mlsanity.com/paper/2311.18803/) (2023)
- [DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2304.06648/) (2023)
- [INTERN: A New Learning Paradigm Towards General Vision](https://mlsanity.com/paper/2111.08687/) (2021)
- [Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification](https://mlsanity.com/paper/2302.08909/) (2023)
- [A Practitioner's Guide to Continual Multimodal Pretraining](https://mlsanity.com/paper/2408.14471/) (2024)
- [Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy](https://mlsanity.com/paper/2203.07845/) (2022)
- [BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity](https://mlsanity.com/paper/2406.17720/) (2024)
- [Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting](https://mlsanity.com/paper/2406.00773/) (2024)
- [Structure-Guided Adversarial Training of Diffusion Models](https://mlsanity.com/paper/2402.17563/) (2024)
- [Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion Model](https://mlsanity.com/paper/2504.01521/) (2025)
- [FungiTastic: A multi-modal dataset and benchmark for image categorization](https://mlsanity.com/paper/2408.13632/) (2024)
- [A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets](https://mlsanity.com/paper/2403.06295/) (2024)
- [Bag of Tricks for Long-Tail Visual Recognition of Animal Species in Camera-Trap Images](https://mlsanity.com/paper/2206.12458/) (2022)
- [GLAMI-1M: A Multilingual Image-Text Fashion Dataset](https://mlsanity.com/paper/2211.14451/) (2022)
- [Fine-Grained Classification for Poisonous Fungi Identification with Transfer Learning](https://mlsanity.com/paper/2407.07492/) (2024)
- [Towards Zero-Shot Camera Trap Image Categorization](https://mlsanity.com/paper/2410.12769/) (2024)
- [BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models](https://mlsanity.com/paper/2510.20095/) (2025)
- [Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling](https://mlsanity.com/paper/2205.05155/) (2022)
- [ViM: Vision Middleware for Unified Downstream Transferring](https://mlsanity.com/paper/2303.06911/) (2023)
- [DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data](https://mlsanity.com/paper/2504.01386/) (2025)
- [Exploring Kolmogorov-Arnold Network Expansions in Vision Transformers for Mitigating Catastrophic Forgetting in Continual Learning](https://mlsanity.com/paper/2507.04020/) (2025)
- [Robust Context-Aware Object Recognition](https://mlsanity.com/paper/2510.00618/) (2025)
- [Training-Free Fine-Grained Semantic Segmentations in Low Data Regimes: A FungiTastic Baseline](https://mlsanity.com/paper/2605.22492/) (2026)
- [On Supernet Transfer Learning for Effective Task Adaptation](https://mlsanity.com/paper/2407.20279/) (2024)
- [Bringing the Context Back into Object Recognition, Robustly](https://mlsanity.com/paper/2411.15933/) (2024)
- [Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance](https://mlsanity.com/paper/2510.12497/) (2025)

## Abstract (arXiv)

We introduce a novel fine-grained dataset and benchmark, the Danish Fungi 2020 (DF20). The dataset, constructed from observations submitted to the Atlas of Danish Fungi, is unique in its taxonomy-accurate class labels, small number of errors, highly unbalanced long-tailed class distribution, rich observation metadata, and well-defined class hierarchy. DF20 has zero overlap with ImageNet, allowing unbiased comparison of models fine-tuned from publicly available ImageNet checkpoints. The proposed evaluation protocol enables testing the ability to improve classification using metadata -- e.g. precise geographic location, habitat, and substrate, facilitates classifier calibration testing, and finally allows to study the impact of the device settings on the classification performance. Experiments using Convolutional Neural Networks (CNN) and the recent Vision Transformers (ViT) show that DF20 presents a challenging task. Interestingly, ViT achieves results superior to CNN baselines with 80.45% accuracy and 0.743 macro F1 score, reducing the CNN error by 9% and 12% respectively. A simple procedure for including metadata into the decision process improves the classification accuracy by more than 2.95 percentage points, reducing the error rate by 15%. The source code for all methods and experiments is available at https://sites.google.com/view/danish-fungi-dataset.