Danish Fungi 2020 -- Not Just Another Image Recognition Dataset

• URL: http://arxiv.org/abs/2103.10107v3
• Date: Mon, 22 Mar 2021 08:43:04 GMT
• Title: Danish Fungi 2020 -- Not Just Another Image Recognition Dataset
• Authors: Luk\'a\v{s} Picek, Milan \v{S}ulc, Ji\v{r}\'i Matas, Jacob Heilmann-Clausen, Thomas S. Jeppesen, Thomas L{\ae}ss{\o}e, Tobias Fr{\o}slev
• Abstract summary: We introduce a novel fine-grained dataset and benchmark, the Danish Fungi 2020 (DF20) The dataset is constructed from observations submitted to the Danish Fungal Atlas. DF20 has zero overlap with ImageNet, allowing unbiased comparison of models fine-tuned from publicly available ImageNet checkpoints.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a novel fine-grained dataset and benchmark, the Danish Fungi 2020 (DF20). The dataset, constructed from observations submitted to the Danish Fungal Atlas, 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 81.25% accuracy, reducing the CNN error by 13%. A baseline procedure for including metadata into the decision process improves the classification accuracy by more than 3.5 percentage points, reducing the error rate by 20%. The source code for all methods and experiments is available at https://sites.google.com/view/danish-fungi-dataset.

Related papers

• Graph Mining under Data scarcity [6.229055041065048]
  We propose an Uncertainty Estimator framework that can be applied on top of any generic Graph Neural Networks (GNNs) We train these models under the classic episodic learning paradigm in the $n$-way, $k$-shot fashion, in an end-to-end setting. Our method outperforms the baselines, which demonstrates the efficacy of the Uncertainty Estimator for Few-shot node classification on graphs with a GNN.
  arXiv  Detail & Related papers  (2024-06-07T10:50:03Z)
• Fuzzy Convolution Neural Networks for Tabular Data Classification [0.0]
  Convolutional neural networks (CNNs) have attracted a great deal of attention due to their remarkable performance in various domains. In this paper, we propose a novel framework fuzzy convolution neural network (FCNN) tailored specifically for tabular data.
  arXiv  Detail & Related papers  (2024-06-04T20:33:35Z)
• A Decade's Battle on Dataset Bias: Are We There Yet? [32.46064586176908]
  We revisit the "dataset classification" experiment suggested by Torralba and Efros a decade ago. Surprisingly, we observe that modern neural networks can achieve excellent accuracy in classifying which dataset an image is from.
  arXiv  Detail & Related papers  (2024-03-13T15:46:37Z)
• Cross-dataset domain adaptation for the classification COVID-19 using chest computed tomography images [0.6798775532273751]
  COVID19-DANet is based on pre-trained CNN backbone for feature extraction. It is tested under four cross-dataset scenarios using the SARS-CoV-2-CT and COVID19-CT datasets.
  arXiv  Detail & Related papers  (2023-11-14T20:36:34Z)
• Do We Really Need a Learnable Classifier at the End of Deep Neural Network? [118.18554882199676]
  We study the potential of learning a neural network for classification with the classifier randomly as an ETF and fixed during training. Our experimental results show that our method is able to achieve similar performances on image classification for balanced datasets.
  arXiv  Detail & Related papers  (2022-03-17T04:34:28Z)
• Attention Mechanism Meets with Hybrid Dense Network for Hyperspectral Image Classification [6.946336514955953]
  Convolutional Neural Networks (CNN) are more suitable, indeed. fixed kernel sizes make traditional CNN too specific, neither flexible nor conducive to feature learning, thus impacting on the classification accuracy. The proposed solution aims at combining the core idea of 3D and 2D Inception net with the Attention mechanism to boost the HSIC CNN performance in a hybrid scenario. The resulting textitattention-fused hybrid network (AfNet) is based on three attention-fused parallel hybrid sub-nets with different kernels in each block repeatedly using high-level features to enhance the final ground-truth maps.
  arXiv  Detail & Related papers  (2022-01-04T06:30:24Z)
• Calibrating Class Activation Maps for Long-Tailed Visual Recognition [60.77124328049557]
  We present two effective modifications of CNNs to improve network learning from long-tailed distribution. First, we present a Class Activation Map (CAMC) module to improve the learning and prediction of network classifiers. Second, we investigate the use of normalized classifiers for representation learning in long-tailed problems.
  arXiv  Detail & Related papers  (2021-08-29T05:45:03Z)
• High performing ensemble of convolutional neural networks for insect pest image detection [124.23179560022761]
  Pest infestation is a major cause of crop damage and lost revenues worldwide. We generate ensembles of CNNs based on different topologies. Two new Adam algorithms for deep network optimization are proposed.
  arXiv  Detail & Related papers  (2021-08-28T00:49:11Z)
• No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data [78.69828864672978]
  A central challenge in training classification models in the real-world federated system is learning with non-IID data. We propose a novel and simple algorithm called Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated ssian mixture model. Experimental results demonstrate that CCVR state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10.
  arXiv  Detail & Related papers  (2021-06-09T12:02:29Z)
• Tent: Fully Test-time Adaptation by Entropy Minimization [77.85911673550851]
  A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy minimization (tent): we optimize the model for confidence as measured by the entropy of its predictions.
  arXiv  Detail & Related papers  (2020-06-18T17:55:28Z)
• Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection [85.53263670166304]
  One-stage detector basically formulates object detection as dense classification and localization. Recent trend for one-stage detectors is to introduce an individual prediction branch to estimate the quality of localization. This paper delves into the representations of the above three fundamental elements: quality estimation, classification and localization.
  arXiv  Detail & Related papers  (2020-06-08T07:24:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.