Danish Fungi 2020 -- Not Just Another Image Recognition Dataset

Abstract

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.

References in corpus (10)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• On Calibration of Modern Neural Networks
• EfficientNetV2: Smaller Models and Faster Training
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
• Evaluating model calibration in classification
• Are we done with ImageNet?
• Plant identification based on noisy web data: the amazing performance of deep learning (LifeCLEF 2017)
• Plant identification in an open-world (LifeCLEF 2016)
• Overview of ExpertLifeCLEF 2018: how far automated identification systems are from the best experts?