Overview of FungiCLEF 2022: Fungi Recognition as
an Open Set Classification Problem
Lukáš Picek1 , Milan Šulc2 , Jiří Matas3 and Jacob Heilmann-Clausen4
1
Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, Czech Republic
2
Rossum.ai, Czech Republic
3
The Center for Machine Perception Dept. of Cybernetics, FEE, Czech Technical University in Prague, Czech Republic
4
Center for Macroecology, Evolution and Climate University of Copenhagen, Denmark
Abstract
The main goal of the new LifeCLEF challenge, FungiCLEF 2022: Fungi Recognition as an Open Set
Classification Problem, was to provide an evaluation ground for end-to-end fungi species recognition in
an open class set scenario. An AI-based fungi species recognition system deployed in the Atlas of Danish
Fungi helps mycologists to collect valuable data and allows users to learn about fungi species identification.
Advances in fungi recognition from images and metadata will allow continuous improvement of the
system deployed in this citizen science project. The training set is based on the Danish Fungi 2020
dataset and contains 295,938 photographs of 1,604 species. For testing, we provided a collection of 59,420
expert-approved observations collected in 2021. The test set includes 1,165 species from the training
set and 1,969 unknown species, leading to an open-set recognition problem. This paper provides (i)
a description of the challenge task and datasets, (ii) a summary of the evaluation methodology, (iii) a
review of the systems submitted by the participating teams, and (iv) a discussion of the challenge results.
Keywords
LifeCLEF, FungiCLEF, fine grained visual categorization, metadata, open-set recognition, fungi, species
identification, machine learning, computer vision, classification
1. Introduction
Automatic recognition of fungi species assists mycologists, citizen scientists and nature enthusi-
asts in species identification in the wild [1, 2]. Its availability supports the collection of valuable
biodiversity data. In practice, species identification typically does not depend solely on the visual
observation of the specimen but also on other information available to the observer — such as
habitat, substrate, location and time. The main goal for the new FungiCLEF competition was to
provide an evaluation ground for automatic methods for fungi recognition in an open class set
scenario, i.e, the submitted methods have to handle images of unknown species. Similarly to
previous LifeCLEF competitions, The competition was hosted on Kaggle primarily to attract
machine learning experts to participate and present their ideas. Thanks to rich metadata, precise
annotations, and baselines available to all competitors, the challenge provides a benchmark for
image recognition with the use of additional information.
CLEF 2022: Conference and Labs of the Evaluation Forum, September 5–8, 2022, Bologna, Italy
$ picekl@kky.zcu.cz (L. Picek)
0000-0002-6041-9722 (L. Picek); 0000-0002-6321-0131 (M. Šulc); 0000-0003-0863-4844 (J. Matas);
0000-0003-4713-6004 (J. Heilmann-Clausen)
© 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
Workshop
Proceedings
http://ceur-ws.org
ISSN 1613-0073 CEUR Workshop Proceedings (CEUR-WS.org)
Figure 1: Three fungi specimen observations from the Atlas of Danish Fungi dataset [4]. Atlas of Danish
Fungi: ©Bedřiška Picková and ©Jan Riis-Hansen and ©Arne Pedersen.
2. Challenge description
The new FungiCLEF 2022 challenge: Fungi Recognition as an Open Set Classification Problem,
was organized in conjunction with the Conference and Labs of the Evaluation Forum (CLEF1 )
and LifeCLEF2 research platform [3], and FGVC9 Workshop3 — The Ninth Workshop on Fine-
Grained Visual Categorization organized within the CVPR conference.
The main goal for this challenge was to return the species with the highest likelihood (or
"unknown") for each given test observation, consisting of a set of images and metadata —
the information about habitat, substrate, location, and more is provided for each observation.
Photographs of unknown fungi species had to be classified into an "unknown" class with label
id −1. The baseline procedure to include metadata in the decision problem and baseline pre-
trained image classifiers were provided as part of the task description to all participants. Sample
observations are visualized in Figure 1. Each row represents one observation.
1
http://www.clef-initiative.eu/
2
http://www.lifeclef.org/
3
https://sites.google.com/view/fgvc9/home
Table 1
FungiCLEF 2022 dataset statistics for each subset.
Subset Species Known Species Unknown Species Images Observations
Training 1,604 1,604 0 266,344 ×
Validation 1,604 1,604 0 29,594 ×
Test 3,134 1,165 1,969 118,676 59,420
2.1. Dataset
The FungiCLEF 2022 dataset is based on data collected through the Atlas of Danish Fungi Web4
and mobile (iOS5 and Android6 ) applications. The Atlas of Danish Fungi is a citizen science
platform with more than 4,000 actively contributing volunteers and with more than 1 million
content-checked observations of approximately 8,650 fungi species.
Development set: For training, the competitors were provided with the DanishFungi 2020
(DF20) dataset [4]. DF20 contains 295,938 images — 266,344 for training and 29,594 for validation
— belonging to 1,604 species. All training samples passed an expert validation process, guar-
anteeing high quality labels. Furthermore, rich observation metadata about habitat, substrate,
time, location, EXIF etc. are provided.
Test set: The test dataset is constructed from all observations submitted in 2021, for which
expert-verified species labels are available. It includes observations collected across all substrate
and habitat types. The test set contains 59,420 observations with 118,676 images belonging
to 3,134 species: 1,165 known from the training set and 1,969 unknown species covering ap-
proximately 30% of the test observations. The test set was further split into public (20%) and
private (80%) subsets — a common practice for Kaggle competitions to prevent participants
from overfitting to the leaderboard.
2.2. Metadata
The visual data is accompanied by metadata for approximately 99% of the image observations
and includes information about attributes related to the environment, place, time and taxonomy.
The provided metadata is acquired by citizen scientists and enables research directions on
combining visual data with metadata. We include 21 frequently filled-in attributes. The most
important attributes are listed and described below.
Substrate: Substrates on which fungi live and fruit are an essential source of information that
helps differentiate similarly-looking species. Each species or genus has its preferable substrate,
and it is rare to find it on other substrates. We provide one of 32 substrate types for more than
99% of images. We differentiate wood of living trees, dead wood, soil, bark, stone, fruits and
others.
4
https://svampe.databasen.org/
5
https://apps.apple.com/us/app/atlas-of-danish-fungi/id1467728588
6
https://play.google.com/store/apps/details?id=com.noque.svampeatlas
Figure 2: Monthly observations distribution in the FungiCLEF 2022 training dataset. Three genera:
Mycena, Boletus, and Exidia. Image taken from [4].
Habitat: While substrate denotes the spots, the habitat indicates the overall environment
where fungi grow, which is vital for fungal recognition. We include the information about the
habitat for 99.5% of observations.
Location: Fungi are highly location-dependent. We include multi-level location informa-
tion. Starting from GPS coordinates with included uncertainty, we further extracted information
about the country, region and district.
Time-Stamp: Observation time is essential for fungi classification in the wild as fruitbod-
ies’ presence depends on seasonality or even the time in a day. Figure 2 shows the monthly
observation frequency for three genera.
EXIF data: Since the camera device and its settings affect the resulting image, the image
classification models may be biased towards specific device attributes. To allow a deeper study
of such phenomena, we include the EXIF data for approximately 84% of images. We included
attributes such as White Balance, Color Space, Metering Mode, Aperture, Device, Exposure
Time and Shutter Speed.
2.3. Timeline
The competition and data were published in February 2022 through the LifeCLEF, Kaggle, and
FGVC challenge pages allowing anyone with research ambitions to register and participate in
the competition. The test data were provided jointly with the training data allowing continuous
evaluation. Each team could submit up to 2 submissions a day. The deadline for challenge sub-
missions was May 16, setting the competition for roughly three months. Participants submitted
CSV files containing the Top1 prediction for each fungi observation. Once the submission phase
was closed (mid-May), the participants were allowed to submit post-competition submissions
to evaluate any exciting findings.
2.4. Evaluation Protocol
The evaluation process consisted of two stages: (i) a public evaluation on the public subset
(20%) of the test set, which was available during the whole competition with a limit of two
submissions a day, and (ii) a final evaluation on the private test set (80%) after the challenge
deadline. The main evaluation metric for the competition was the F𝑚 1 , defined as the mean of
class-wise F1 scores:
𝑁
1 ∑︁
F𝑚
1 = 𝐹1 , (1)
𝑁 𝑠=1 𝑠
where 𝑁 represents the number of classes — in case of the Kaggle evaluation, 𝑁 = 1, 165
(#classes in the test set) – and 𝑠 is the species index. The F1 score for each class is calculated as
a harmonic mean of the class precision 𝑃𝑆 and recall 𝑅𝑆 :
𝑃𝑠 × 𝑅𝑠 tp𝑠 tp𝑠
𝐹1𝑠 = 2 × , 𝑃𝑠 = , 𝑅𝑠 = (2)
𝑃𝑠 + 𝑅𝑠 tp𝑠 + fp𝑠 tp𝑠 + fn𝑠
In single-label multi-class classification, the True Positives (tp) of a species represents the
number of correct Top1 predictions of that species, False Positive (fp) denotes how many times
was different species predicted instead of the (tp), and False Negatives (fn) indicates how many
images of species 𝑠 have been wrongly classified.
2.5. Working Notes
All participants with valid submissions were asked to provide a Working Note paper — a technical
report with information needed to reproduce the results of all submissions. All submit-
ted Working Notes were reviewed by 2–3 reviewers. The review process was single-blind
and offered up to two rebuttals. The acceptance rate was 75%.
3. Challenge Results
The official challenge results, based on the F𝑚 1 score, are displayed in Figure 3. The best
performing team — xiong — achieved F1 of 80.43% on the private test set and an accuracy of
𝑚
65.69% on the complete test set. We note that the order would be different in terms of accuracy,
as shown in Figure 4, where the best accuracy of 67.08% on the full rest set was achieved by
team GG, primarily due to a high number of correctly identified out-of-scope observations. In
the case of the out-of-scope (OoS) identification performance, i.e. what proportion of out-of-
scope observations has been correctly classified as OoS, the best performing team with 44.55%
correctly categorized observations was one of the worst-performing teams in terms of F𝑚 1 . As
also displayed in Figure 4 participants identified less than 5% OoS observations and only four
teams achieved accuracy over 10% on out-of-scope observations. In Figure 5 we have evaluated
the species toxicity confusion on the full test set for all the participants, i.e., how often poisonous
species are confused for edible ones and vice versa. Interestingly, the more critical confusion
where poisonous fungi were misclassified as edible is relatively high even for the best scoring
models — 5.70% and 6.63% for team GG and team xiong, respectively.
Accuracy [%] Macro averaged F1 [%]
0
10
20
30
40
50
60
70
80
0
20
40
60
65.69 80 83.78
xiong 6.85 xiong 80.43
base 65.08 base 83.46
5.07 79.76
63.57 82.98
observations.
USTC-IAT- United 0.04 USTC-IAT- United 79.06
GG 67.08 GG 82.21
16.06 78.91
LOL 0 63.57 LOL 80.84
77.91
TeamSpirit 65.1 TeamSpirit 80.54
11.13 77.58
Stefan 64.78 Stefan 80.62
6.14 77.54
bear~ 0 63.34 bear~ 80.35
77.44
wangzhe 0 63.11 wangzhe 81.44
77.42
Klawens 0 62.92 Klawens 80.64
76.43
Harry Potterhehe 64.63 Harry Potterhehe 79.57
10.45 76.34
HaHaWork 0 62.98 HaHaWork 80.21
76.02
62.57 80.77
4. Participants and Methods
X 0 X 75.56
Rziting 0 62.34 Rziting 78.26
74.16
withHaiHaiLife 0 62.21 withHaiHaiLife 78.46
74.03
Goweild 0 61.4 Goweild 75.16
71.91
philomel 0 60.12 philomel 71.77
68.89
60.96 71.81
ensuring a sufficient level of reproducibility and quality.
Mingle1994 1.86 Mingle1994 68.15
mengyao01 0 60.19 mengyao01 71.49
67.86
liuaihong 0 58.32 liuaihong 69.38
66.37
here weli 0 57.11 here weli 66.36
63.84
RongRongXue 0 57.03 RongRongXue 66.65
63.49
MAGUS_YWX 57.7 MAGUS_YWX 63.76
5.5 61.97
KDELab 0 54.52 KDELab 62.25
58.5
asdaas1 0.27 53.8 asdaas1 61.09
58.06
YHT_MT1 0.04 52.97 YHT_MT1 59.66
56.44
cmj 0 51.19 cmj 55.29
52.23
Full Test Set
Gaurav 0 46.8 Gaurav 50.23
47.38
38.98 Duong Anh Kiet 35.28
Figure 3: Official FungiCLEF 2022 competition results, sorted by performance on the private set.
Duong Anh Kiet 0 31.73
44.02 34.43
Public leaderboard
arcsin2 44.55 arcsin2 31.46
Out-of-the Scope [Binary]
Private Leaderboard
we summarize the approach of teams with published working notes. More details can be found
scope observations has been correctly classified as out-of-scope, compared to the accuracy over all
The results on the public and private test sets (leaderboards) are displayed in Figure 3. Below
in the individual working notes of participants [5, 6, 7, 8, 9, 10] which passed the review process,
Figure 4: Out-of-scope identification performance on the full test set, i.e. what proportion of out-of-
In total, 38 teams contributed with 701 valid submissions to the challenge evaluation on Kaggle.
60 Edible --> Poisonous
54.12
Poisonous --> Edible
50
38.51
Species Confusion [%]
40
32.14
30
23.28
18.45
17.4
15.73
20
14.61
12.38
12.32
11.95
philomel 0.24 9.47
9.35
Goweild 0.19 8.73
Mingle1994 0.52 8.67
Klawens 0.1 8.24
withHaiHaiLife 0.14 7.93
Harry Potterhehe 2.64 7.55
USTC-IAT- United 0.1 7.31
X 0.11 7.24
Rziting 0.15 7.12
HaHaWork 0.13 7.06
10
6.93
wangzhe 0.1 6.81
base 0.62 6.69
Stefan 0.57 6.69
xiong 0.67 6.63
bear~ 0.11 6.63
5.7
TeamSpirit 2.527
3.58
MAGUS_YWX 2.44
arcsin2 2.17
Duong Anh Kiet 1.03
Gaurav 0.66
YHT_MT1 0.42
KDELab 0.41
here weli 0.39
asdaas1 0.36
RongRongXue 0.33
liuaihong 0.29
cmj 0.28
mengyao01 0.2
0.1
0
GG
LOL
Figure 5: Species toxicity confusion on the full test set: Poisonous –> Edible denotes poisonous fungi that
were misclassified as edible, and Edible –> Poisonous denotes edible fungi misclassified as poisonous.
xiong [6]: The winning submission by Xiong et al., achieving an impressive F𝑚 1 score of 80.43%
on the private test set, used an ensemble of MetaFormer [11] and ConvNext [12] networks.
The provided metadata were utilized as inputs to the MetaFormer architecture. To battle the
long-tailed distribution of species, the authors used the Seasaw loss [13]. Additional improve-
ments were achieved by test-time augmentation, adding a model trained with pseudo-labels to
the ensemble, and adding a thresholding post-processing to deal with out-of-scope observations.
USTC-IAT-United [7]: The submission by Yu et al. used an ensemble of several CNN and Trans-
former architectures: Metaformer [11], SwinTransformer[14], EfficientNet [15], ViT (Vision
Transformer) [16], BEiT [17]. The team scored 3rd with 79.06% of F𝑚 1 score on the private test set.
In their working notes, the authors explore the impact of different data augmentation techniques,
model architectures, loss functions, and attention mechanisms on the classification performance.
GG [8]: Shen et al. introduced a novel architecture CoLKANet based on VAN (Visual At-
tention Network) [18] and CoAtNet [19]. It is a combination of large kernel attention and vision
transformer. The proposed CoLKANet outperforms Swin [14] and VOLO [20] models in terms
of F𝑚
1 by 2.3 and 1.9 percentage points, respectively. ConvNeXt [12] performed similarly to
the proposed CoLKANet architecture. Furthermore, the team used techniques such as Label
Aware Smoothing [21], Pseudo labelling for tail classes and various augmentation techniques.
When TrivialAugment [22] was deployed during the middle stage of experimentation, the team
observed a rise in F𝑚
1 of around 0.5%. Progressively, Random Erasing [23], CutMix [24] and
Mixup [25] were added, which helped with regularization. The final submission score was
achieved by an ensemble of five models: 2× ConvNeXt, VOLO, Swin, and CoLKANet. The novel
CoLKANet is an interesting contribution with potential outside this competition’s scope.
TeamSpirit [5]: Fan et al., who scored sixth in the challenge with 77.58% F𝑚1 score, propose an
image classification method called Class-wise Weighted Prototype Classifier. CWPC decouples
closed-set training and open-set inference by constructing class centers from the training set
features and their prediction scores. A hard classes mining strategy and the LDAM loss [26]
were used to cope with the long-tailed distribution of species. This team encoded the metadata
using a multilingual BERT model [27] with RoBERTa [28].
Stefan [10]: Wolf and Beyerer refrained from using ensembles of multiple models, and —
for the sake of model simplicity — focused on developing a strong single-model submission.
The method is based on a Swin Transformer Large backbone [14], a class-balancing training
scheme [29], heavy data augmentation [30] and thresholding the softmax scores to cope with
out-of-scope observations. The team scored 7th , in the challenge with 77.54% F𝑚
1 score.
SSN [9]:This team experimented with several ResNet [31], ResNeXt [32], and EfficientNet [33]
architectures. For their best submission, feature vectors from two selected architectures, Effi-
cientNetB4 and ResNeXt101, were concatenated with a categorical representation of metadata.
The resulted features were later used for training the XGBoost Ensemble Classifier [34]. An
interesting benefit of the XGBoost algorithm is that the relative importance of the ensembled
features is computed; thus, each feature might be observed and studied. With an absolute
F𝑚
1 performance of 48.96%, the XGBoost algorithm with two CNN backbones poses a unique
approach for the classification, even though performing worst compared to other participants.
5. Conclusions
This paper presents an overview and results of the first edition of the FungiCLEF challenge
organized in conjunction with the Conference and Labs of the Evaluation Forum (CLEF7 ),
LifeCLEF8 research platform [35] and FGVC.
All submissions with working notes were based on modern Convolutional Neural Network
(CNN) or transformer-inspired architectures, such as Metaformer [11], Swin Transformer [14],
and BEiT [17]. The best performing teams used ensembles of both CNNs and Transformers.
The winning team [6] achieved 80.43% accuracy with a combination of ConvNext-large [12] and
MetaFormer [11]. The results were often improved by combining predictions belonging to the
same observation and by both training-time and test-time data augmentations.
Participants experimented with a number of different training losses to battle the long tail
distribution and fine-grained classification with small inter-class differences and large intra-
class differences: besides the standard Cross Entropy loss function, we have seen successful
applications of the Seesaw loss [13], Focal loss [36], Arcface loss [37], Sub-Center loss [38] and
Adaptive Margin [39].
We were happy to see the participants experimented with different use of the provided
7
http://www.clef-initiative.eu/
8
http://www.lifeclef.org/
observation metadata, which often lead to improvements in the recognition scores. Besides the
probabilistic baseline published with the dataset [4], we have seen hand-crafted encoding of the
metadata into feature vectors, as well as encoding of the metadata with a multilingual BERT
model [27] and RoBERTa [28]. The metadata were then combined with image features extracted
from a CNN or Transformer image classifier, or directly used as an input to Metaformer [11].
The results of participants’ comprehensive experiments with model architectures, loss func-
tions and usage of metadata in fine-grained image-classification will help to improve species
recognition services that aid researchers, citizen-science communities and nature enthusiasts.
As discussed in Section 3, there is still a great space for improvement in the recognition of
out-of-scope classes. Our evaluation of classification errors identified that confusion of poi-
sonous mushrooms for edible is much more common than confusion of edible mushrooms for
poisonous. This could be critical in applications that may affect the decision to consume a
mushroom, and presents an important aspect to address in the future work.
Acknowledgments
LP was supported by the UWB grant, project No. SGS-2022-017. LP was supported by the
Technology Agency of the Czech Republic, project No. SS05010008.
References
[1] M. Šulc, L. Picek, J. Matas, T. Jeppesen, J. Heilmann-Clausen, Fungi recognition: A practical
use case, in: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer
Vision, 2020, pp. 2316–2324.
[2] L. Picek, M. Šulc, J. Matas, J. Heilmann-Clausen, T. S. Jeppesen, E. Lind, Automatic fungi
recognition: Deep learning meets mycology, Sensors 22 (2022) 633.
[3] A. Joly, H. Goëau, S. Kahl, L. Picek, T. Lorieul, E. Cole, B. Deneu, M. Servajean, A. Durso,
H. Glotin, R. Planqué, W.-P. Vellinga, A. Navine, H. Klinck, T. Denton, I. Eggel, P. Bonnet,
M. Šulc, M. Hruz, Overview of lifeclef 2022: an evaluation of machine-learning based
species identification and species distribution prediction, in: International Conference of
the Cross-Language Evaluation Forum for European Languages, Springer, 2022.
[4] L. Picek, M. Šulc, J. Matas, T. S. Jeppesen, J. Heilmann-Clausen, T. Læssøe, T. Frøslev,
Danish fungi 2020-not just another image recognition dataset, in: Proceedings of the
IEEE/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 1525–1535.
[5] G. Fan, C. Zining, W. Weiqiu, S. Yinan, S. Fei, Z. Zhicheng, C. Hong, Does closed-set
training generalize to open-set recognition?, in: Working Notes of CLEF 2022 - Conference
and Labs of the Evaluation Forum, 2022.
[6] Z. Xiong, Y. Ruan, Y. Hu, Y. Zhang, Y. Zhu, S. Guo, W. Zhu, B. Han, An empirical study for
fine-grained fungi recognition with transformer and convnet, in: Working Notes of CLEF
2022 - Conference and Labs of the Evaluation Forum, 2022.
[7] J. Yu, H. Chang, K. Lu, G. Xie, L. Zhang, Z. Cai, S. Du, Z. Wei, Z. Liu, F. Gao, F. Shuang,
Bag of tricks and a strong baseline for fgvc, in: Working Notes of CLEF 2022 - Conference
and Labs of the Evaluation Forum, 2022.
[8] Y. Shen, X. Sun, Z. Zhu, When large kernel meets vision transformer: A solution for
snakeclef & fungiclef, in: Working Notes of CLEF 2022 - Conference and Labs of the
Evaluation Forum, 2022.
[9] K. Desingu, A. Bhaskar, M. Palaniappan, E. A. Chodisetty, H. Bharathi, Classification
of fungi species: A deep learning based image feature extraction and gradient boosting
ensemble approach, in: Working Notes of CLEF 2022 - Conference and Labs of the
Evaluation Forum, 2022.
[10] S. Wolf, J. Beyerer, Transformer-based fine-grained fungi classification in an open-set
scenario, in: Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum,
2022.
[11] Q. Diao, Y. Jiang, B. Wen, J. Sun, Z. Yuan, Metaformer: A unified meta framework for
fine-grained recognition, arXiv preprint arXiv:2203.02751 (2022).
[12] Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, S. Xie, A convnet for the 2020s, in:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,
2022, pp. 11976–11986.
[13] J. Wang, W. Zhang, Y. Zang, Y. Cao, J. Pang, T. Gong, K. Chen, Z. Liu, C. C. Loy, D. Lin,
Seesaw loss for long-tailed instance segmentation, in: Proceedings of the IEEE/CVF
Conference on Computer Vision and Pattern Recognition, 2021, pp. 9695–9704.
[14] Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo, Swin transformer: Hierarchical
vision transformer using shifted windows, in: Proceedings of the IEEE/CVF International
Conference on Computer Vision, 2021, pp. 10012–10022.
[15] M. Tan, Q. Le, Efficientnet: Rethinking model scaling for convolutional neural networks,
in: International conference on machine learning, PMLR, 2019, pp. 6105–6114.
[16] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. De-
hghani, M. Minderer, G. Heigold, S. Gelly, et al., An image is worth 16x16 words: Trans-
formers for image recognition at scale, arXiv preprint arXiv:2010.11929 (2020).
[17] H. Bao, L. Dong, F. Wei, Beit: Bert pre-training of image transformers, arXiv preprint
arXiv:2106.08254 (2021).
[18] M.-H. Guo, C.-Z. Lu, Z.-N. Liu, M.-M. Cheng, S.-M. Hu, Visual attention network, arXiv
preprint arXiv:2202.09741 (2022).
[19] Z. Dai, H. Liu, Q. V. Le, M. Tan, Coatnet: Marrying convolution and attention for all data
sizes, Advances in Neural Information Processing Systems 34 (2021) 3965–3977.
[20] L. Yuan, Q. Hou, Z. Jiang, J. Feng, S. Yan, Volo: Vision outlooker for visual recognition,
arXiv preprint arXiv:2106.13112 (2021).
[21] Z. Zhong, J. Cui, S. Liu, J. Jia, Improving calibration for long-tailed recognition, in:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,
2021, pp. 16489–16498.
[22] S. G. Müller, F. Hutter, Trivialaugment: Tuning-free yet state-of-the-art data augmentation,
in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp.
774–782.
[23] Z. Zhong, L. Zheng, G. Kang, S. Li, Y. Yang, Random erasing data augmentation, in:
Proceedings of the AAAI conference on artificial intelligence, volume 34, 2020, pp. 13001–
13008.
[24] S. Yun, D. Han, S. J. Oh, S. Chun, J. Choe, Y. Yoo, Cutmix: Regularization strategy to train
strong classifiers with localizable features, in: Proceedings of the IEEE/CVF international
conference on computer vision, 2019, pp. 6023–6032.
[25] H. Zhang, M. Cisse, Y. N. Dauphin, D. Lopez-Paz, mixup: Beyond empirical risk minimiza-
tion, arXiv preprint arXiv:1710.09412 (2017).
[26] K. Cao, C. Wei, A. Gaidon, N. Arechiga, T. Ma, Learning imbalanced datasets with label-
distribution-aware margin loss, Advances in neural information processing systems 32
(2019).
[27] J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional
transformers for language understanding, arXiv preprint arXiv:1810.04805 (2018).
[28] Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer,
V. Stoyanov, Roberta: A robustly optimized bert pretraining approach, arXiv preprint
arXiv:1907.11692 (2019).
[29] A. Gupta, P. Dollar, R. Girshick, Lvis: A dataset for large vocabulary instance segmentation,
in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition,
2019, pp. 5356–5364.
[30] E. D. Cubuk, B. Zoph, J. Shlens, Q. V. Le, Randaugment: Practical automated data aug-
mentation with a reduced search space, in: Proceedings of the IEEE/CVF conference on
computer vision and pattern recognition workshops, 2020, pp. 702–703.
[31] K. He, X. Zhang, S. Ren, J. Sun, Deep Residual Learning for Image Recognition, in:
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
2016.
[32] S. Xie, R. Girshick, P. Dollar, Z. Tu, K. He, Aggregated Residual Transformations for Deep
Neural Networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition (CVPR), 2017.
[33] M. Tan, Q. Le, Efficientnet: Rethinking model scaling for convolutional neural networks,
in: International Conference on Machine Learning, PMLR, 2019, pp. 6105–6114.
[34] T. Chen, C. Guestrin, XGBoost: A scalable tree boosting system, in: Proceedings of the
22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,
KDD ’16, ACM, New York, NY, USA, 2016, pp. 785–794. URL: http://doi.acm.org/10.1145/
2939672.2939785. doi:10.1145/2939672.2939785.
[35] A. Joly, H. Goëau, S. Kahl, L. Picek, T. Lorieul, E. Cole, B. Deneu, M. Servajean, R. Ruiz De
Castañeda, I. Bolon, H. Glotin, R. Planqué, W.-P. Vellinga, A. Dorso, H. Klinck, T. Denton,
I. Eggel, P. Bonnet, H. Müller, Overview of lifeclef 2021: a system-oriented evaluation of
automated species identification and species distribution prediction, in: Proceedings of
the Twelfth International Conference of the CLEF Association (CLEF 2021), 2021.
[36] T.-Y. Lin, P. Goyal, R. Girshick, K. He, P. Dollár, Focal loss for dense object detection, in:
Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980–2988.
[37] J. Deng, J. Guo, N. Xue, S. Zafeiriou, Arcface: Additive angular margin loss for deep face
recognition, in: Proceedings of the IEEE/CVF conference on computer vision and pattern
recognition, 2019, pp. 4690–4699.
[38] J. Deng, J. Guo, T. Liu, M. Gong, S. Zafeiriou, Sub-center arcface: Boosting face recognition
by large-scale noisy web faces, in: European Conference on Computer Vision, Springer,
2020, pp. 741–757.
[39] H. Liu, X. Zhu, Z. Lei, S. Z. Li, Adaptiveface: Adaptive margin and sampling for face
recognition, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern
Recognition, 2019, pp. 11947–11956.