Yue Fan (PhD Student)

MSc Yue Fan

Address: Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
Location: E1 4 - 608
Phone: +49 681 9325 2138
Fax: +49 681 9325 2099
E-mail: Get email via email

Personal Information

Publications

2023

Conference paper

H. Chen, R. Tao, Y. Fan, Y. Wang, M. Savvides, J. Wang, B. Raj, X. Xie, and B. Schiele

“SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised Learning,” in Eleventh International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda.

@inproceedings{Chen_ICLR23,
TITLE = {{SoftMatch}: {A}ddressing the Quantity-Quality Tradeoff in Semi-supervised Learning},
AUTHOR = {Chen, H. and Tao, R. and Fan, Yue and Wang, Y. and Savvides, M. and Wang, J. and Raj, B. and Xie, X. and Schiele, Bernt},
LANGUAGE = {eng},
PUBLISHER = {OpenReview.net},
YEAR = {2023},
PUBLREMARK = {Accepted},
MARGINALMARK = {$\bullet$},
BOOKTITLE = {Eleventh International Conference on Learning Representations (ICLR 2023)},
ADDRESS = {Kigali, Rwanda},
}

Endnote

%0 Conference Proceedings
%A Chen, H.
%A Tao, R.
%A Fan, Yue
%A Wang, Y.
%A Savvides, M.
%A Wang, J.
%A Raj, B.
%A Xie, X.
%A Schiele, Bernt
%+ External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
External Organizations
External Organizations
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised Learning : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000C-73BD-E
%D 2023
%B Eleventh International Conference on Learning Representations
%Z date of event: 2023-05-01 - 2023-05-05
%C Kigali, Rwanda
%B Eleventh International Conference on Learning Representations
%I OpenReview.net

Conference paper

Y. Wang, H. Chen, Q. Heng, W. Hou, Y. Fan, Z. Wu, J. Wang, M. Savvides, T. Shinozaki, B. Raj, B. Schiele, and X. Xie

“FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning,” in Eleventh International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda.

@inproceedings{Wang_ICLR2023,
TITLE = {{FreeMatch}: Self-adaptive Thresholding for Semi-supervised Learning},
AUTHOR = {Wang, Yidong and Chen, Hao and Heng, Qiang and Hou, Wenxin and Fan, Yue and Wu, Zhen and Wang, Jindong and Savvides, Marios and Shinozaki, Takahiro and Raj, Bhiksha and Schiele, Bernt and Xie, Xing},
LANGUAGE = {eng},
PUBLISHER = {OpenReview.net},
YEAR = {2023},
PUBLREMARK = {Accepted},
MARGINALMARK = {$\bullet$},
BOOKTITLE = {Eleventh International Conference on Learning Representations (ICLR 2023)},
ADDRESS = {Kigali, Rwanda},
}

Endnote

%0 Conference Proceedings
%A Wang, Yidong
%A Chen, Hao
%A Heng, Qiang
%A Hou, Wenxin
%A Fan, Yue
%A Wu, Zhen
%A Wang, Jindong
%A Savvides, Marios
%A Shinozaki, Takahiro
%A Raj, Bhiksha
%A Schiele, Bernt
%A Xie, Xing
%+ External Organizations
External Organizations
External Organizations
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
External Organizations
External Organizations
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
%T FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000C-1846-B
%D 2023
%B Eleventh International Conference on Learning Representations
%Z date of event: 2023-05-01 - 2023-05-05
%C Kigali, Rwanda
%B Eleventh International Conference on Learning Representations
%I OpenReview.net

Conference paper

Y. Fan, A. Kukleva, D. Dai, and B. Schiele

“SSB: Simple but Strong Baseline for Boosting Performance of Open-Set Semi-Supervised Learning,” in IEEE/CVF International Conference on Computer Vision (ICCV 2023), Paris, France, 2023.

@inproceedings{Fan_ICCV23,
TITLE = {SSB: {S}imple but Strong Baseline for Boosting Performance of Open-Set Semi-Supervised Learning},
AUTHOR = {Fan, Yue and Kukleva, Anna and Dai, Dengxin and Schiele, Bernt},
LANGUAGE = {eng},
ISBN = {979-8-3503-0718-4},
DOI = {10.1109/ICCV51070.2023.01472},
PUBLISHER = {IEEE},
YEAR = {2023},
MARGINALMARK = {$\bullet$},
DATE = {2023},
BOOKTITLE = {IEEE/CVF International Conference on Computer Vision (ICCV 2023)},
PAGES = {16022--16032},
ADDRESS = {Paris, France},
}

Endnote

%0 Conference Proceedings
%A Fan, Yue
%A Kukleva, Anna
%A Dai, Dengxin
%A Schiele, Bernt
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T SSB: Simple but Strong Baseline for Boosting Performance of Open-Set Semi-Supervised Learning  : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000D-F984-5
%R 10.1109/ICCV51070.2023.01472
%D 2023
%B IEEE/CVF International Conference on Computer Vision
%Z date of event: 2023-10-02 - 2023-10-06
%C Paris, France
%B IEEE/CVF International Conference on Computer Vision
%P 16022 - 16032
%I IEEE
%@ 979-8-3503-0718-4

Article

Y. Fan, A. Kukleva, D. Dai, and B. Schiele

“Revisiting Consistency Regularization for Semi-supervised Learning,” International Journal of Computer Vision, vol. 131, 2023.

@article{Fan22,
TITLE = {Revisiting Consistency Regularization for Semi-supervised Learning},
AUTHOR = {Fan, Yue and Kukleva, Anna and Dai, Dengxin and Schiele, Bernt},
LANGUAGE = {eng},
ISSN = {0920-5691},
DOI = {10.1007/s11263-022-01723-4},
PUBLISHER = {Springer},
ADDRESS = {New York, NY},
YEAR = {2023},
MARGINALMARK = {$\bullet$},
DATE = {2023},
JOURNAL = {International Journal of Computer Vision},
VOLUME = {131},
PAGES = {626--643},
}

Endnote

%0 Journal Article
%A Fan, Yue
%A Kukleva, Anna
%A Dai, Dengxin
%A Schiele, Bernt
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Revisiting Consistency Regularization for Semi-supervised Learning : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000C-73A9-4
%R 10.1007/s11263-022-01723-4
%7 2022
%D 2023
%J International Journal of Computer Vision
%O Int. J. Comput. Vis.
%V 131
%& 626
%P 626 - 643
%I Springer
%C New York, NY
%@ false

2022

Conference paper

D4D2

Y. Wang, H. Chen, Y. Fan, W. Sun, R. Tao, W. Hou, R. Wang, L. Yang, Z. Zhou, L.-Z. Guo, H. Qi, Z. Wu, Y.-F. Li, S. Nakamura, W. Ye, M. Savvides, B. Raj, T. Shinozaki, B. Schiele, J. Wang, X. Xie, and Y. Zhang

“USB: A Unified Semi-supervised Learning Benchmark for Classification,” in Advances in Neural Information Processing Systems 35 (NeurIPS 2022), New Orleans, LA, USA, 2022.

@inproceedings{Wang_Neurips22,
TITLE = {{USB}: {A} Unified Semi-supervised Learning Benchmark for Classification},
AUTHOR = {Wang, Yidong and Chen, Hao and Fan, Yue and Sun, Wang and Tao, Ran and Hou, Wenxin and Wang, Renjie and Yang, Linyi and Zhou, Zhi and Guo, Lan-Zhe and Qi, Heli and Wu, Zhen and Li, Yu-Feng and Nakamura, Satoshi and Ye, Wei and Savvides, Marios and Raj, Bhiksha and Shinozaki, Takahiro and Schiele, Bernt and Wang, Jindong and Xie, Xing and Zhang, Yue},
LANGUAGE = {eng},
PUBLISHER = {Curran Associates, Inc.},
YEAR = {2022},
MARGINALMARK = {$\bullet$},
BOOKTITLE = {Advances in Neural Information Processing Systems 35 (NeurIPS 2022)},
EDITOR = {Koyejo, S. and Mohamed, S. and Agarwal, A. and Belgrave, D. and Cho, K. and Oh, A.},
PAGES = {3938--3961},
ADDRESS = {New Orleans, LA, USA},
}

Endnote

%0 Conference Proceedings
%A Wang, Yidong
%A Chen, Hao
%A Fan, Yue
%A Sun, Wang
%A Tao, Ran
%A Hou, Wenxin
%A Wang, Renjie
%A Yang, Linyi
%A Zhou, Zhi
%A Guo, Lan-Zhe
%A Qi, Heli
%A Wu, Zhen
%A Li, Yu-Feng
%A Nakamura, Satoshi
%A Ye, Wei
%A Savvides, Marios
%A Raj, Bhiksha
%A Shinozaki, Takahiro
%A Schiele, Bernt
%A Wang, Jindong
%A Xie, Xing
%A Zhang, Yue
%+ Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
Computer Graphics, MPI for Informatics, Max Planck Society
%T USB: A Unified Semi-supervised Learning Benchmark for Classification : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000C-184A-7
%D 2022
%B 36th Conference on Neural Information Processing Systems
%Z date of event: 2022-11-28 - 2022-12-09
%C New Orleans, LA, USA
%B Advances in Neural Information Processing Systems 35
%E Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; Oh, A.
%P 3938 - 3961
%I Curran Associates, Inc.
%U https://openreview.net/pdf?id=QeuwINa96C

Conference paper

Y. Fan, D. Dai, and B. Schiele

“CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.

Abstract

In this paper, we propose a novel co-learning framework (CoSSL) with
decoupled representation learning and classifier learning for imbalanced SSL.
To handle the data imbalance, we devise Tail-class Feature Enhancement (TFE)
for classifier learning. Furthermore, the current evaluation protocol for
imbalanced SSL focuses only on balanced test sets, which has limited
practicality in real-world scenarios. Therefore, we further conduct a
comprehensive evaluation under various shifted test distributions. In
experiments, we show that our approach outperforms other methods over a large
range of shifted distributions, achieving state-of-the-art performance on
benchmark datasets ranging from CIFAR-10, CIFAR-100, ImageNet, to Food-101. Our
code will be made publicly available.

BibTeX

@inproceedings{Fan_CVPR2022,
TITLE = {{CoSSL}: {C}o-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning},
AUTHOR = {Fan, Yue and Dai, Dengxin and Schiele, Bernt},
LANGUAGE = {eng},
ISBN = {978-1-6654-6946-3},
DOI = {10.1109/CVPR52688.2022.01417},
PUBLISHER = {IEEE},
YEAR = {2022},
MARGINALMARK = {$\bullet$},
ABSTRACT = {In this paper, we propose a novel co-learning framework (CoSSL) with<br>decoupled representation learning and classifier learning for imbalanced SSL.<br>To handle the data imbalance, we devise Tail-class Feature Enhancement (TFE)<br>for classifier learning. Furthermore, the current evaluation protocol for<br>imbalanced SSL focuses only on balanced test sets, which has limited<br>practicality in real-world scenarios. Therefore, we further conduct a<br>comprehensive evaluation under various shifted test distributions. In<br>experiments, we show that our approach outperforms other methods over a large<br>range of shifted distributions, achieving state-of-the-art performance on<br>benchmark datasets ranging from CIFAR-10, CIFAR-100, ImageNet, to Food-101. Our<br>code will be made publicly available.<br>},
BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)},
PAGES = {14554--14564},
ADDRESS = {New Orleans, LA, USA},
}

Endnote

%0 Conference Proceedings
%A Fan, Yue
%A Dai, Dengxin
%A Schiele, Bernt
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000A-16BA-C
%R 10.1109/CVPR52688.2022.01417
%D 2022
%B 35th IEEE/CVF Conference on Computer Vision and Pattern Recognition
%Z date of event: 2022-06-19 - 2022-06-24
%C New Orleans, LA, USA
%X   In this paper, we propose a novel co-learning framework (CoSSL) with<br>decoupled representation learning and classifier learning for imbalanced SSL.<br>To handle the data imbalance, we devise Tail-class Feature Enhancement (TFE)<br>for classifier learning. Furthermore, the current evaluation protocol for<br>imbalanced SSL focuses only on balanced test sets, which has limited<br>practicality in real-world scenarios. Therefore, we further conduct a<br>comprehensive evaluation under various shifted test distributions. In<br>experiments, we show that our approach outperforms other methods over a large<br>range of shifted distributions, achieving state-of-the-art performance on<br>benchmark datasets ranging from CIFAR-10, CIFAR-100, ImageNet, to Food-101. Our<br>code will be made publicly available.<br>
%K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Learning, cs.LG
%B IEEE/CVF Conference on Computer Vision and Pattern Recognition
%P 14554 - 14564
%I IEEE
%@ 978-1-6654-6946-3

Paper

H. Chen, Y. Fan, Y. Wang, J. Wang, B. Schiele, X. Xie, M. Savvides, and B. Raj

“An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning,” 2022. [Online]. Available: https://arxiv.org/abs/2211.11086.

Abstract

Semi-supervised learning (SSL) has shown great promise in leveraging
unlabeled data to improve model performance. While standard SSL assumes uniform
data distribution, we consider a more realistic and challenging setting called
imbalanced SSL, where imbalanced class distributions occur in both labeled and
unlabeled data. Although there are existing endeavors to tackle this challenge,
their performance degenerates when facing severe imbalance since they can not
reduce the class imbalance sufficiently and effectively. In this paper, we
study a simple yet overlooked baseline -- SimiS -- which tackles data imbalance
by simply supplementing labeled data with pseudo-labels, according to the
difference in class distribution from the most frequent class. Such a simple
baseline turns out to be highly effective in reducing class imbalance. It
outperforms existing methods by a significant margin, e.g., 12.8%, 13.6%, and
16.7% over previous SOTA on CIFAR100-LT, FOOD101-LT, and ImageNet127
respectively. The reduced imbalance results in faster convergence and better
pseudo-label accuracy of SimiS. The simplicity of our method also makes it
possible to be combined with other re-balancing techniques to improve the
performance further. Moreover, our method shows great robustness to a wide
range of data distributions, which holds enormous potential in practice. Code
will be publicly available.

BibTeX

@online{Chen2211.11086,
TITLE = {An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning},
AUTHOR = {Chen, Hao and Fan, Yue and Wang, Yidong and Wang, Jindong and Schiele, Bernt and Xie, Xing and Savvides, Marios and Raj, Bhiksha},
LANGUAGE = {eng},
URL = {https://arxiv.org/abs/2211.11086},
EPRINT = {2211.11086},
EPRINTTYPE = {arXiv},
YEAR = {2022},
MARGINALMARK = {$\bullet$},
ABSTRACT = {Semi-supervised learning (SSL) has shown great promise in leveraging<br>unlabeled data to improve model performance. While standard SSL assumes uniform<br>data distribution, we consider a more realistic and challenging setting called<br>imbalanced SSL, where imbalanced class distributions occur in both labeled and<br>unlabeled data. Although there are existing endeavors to tackle this challenge,<br>their performance degenerates when facing severe imbalance since they can not<br>reduce the class imbalance sufficiently and effectively. In this paper, we<br>study a simple yet overlooked baseline -- SimiS -- which tackles data imbalance<br>by simply supplementing labeled data with pseudo-labels, according to the<br>difference in class distribution from the most frequent class. Such a simple<br>baseline turns out to be highly effective in reducing class imbalance. It<br>outperforms existing methods by a significant margin, e.g., 12.8%, 13.6%, and<br>16.7% over previous SOTA on CIFAR100-LT, FOOD101-LT, and ImageNet127<br>respectively. The reduced imbalance results in faster convergence and better<br>pseudo-label accuracy of SimiS. The simplicity of our method also makes it<br>possible to be combined with other re-balancing techniques to improve the<br>performance further. Moreover, our method shows great robustness to a wide<br>range of data distributions, which holds enormous potential in practice. Code<br>will be publicly available.<br>},
}

Endnote

%0 Report
%A Chen, Hao
%A Fan, Yue
%A Wang, Yidong
%A Wang, Jindong
%A Schiele, Bernt
%A Xie, Xing
%A Savvides, Marios
%A Raj, Bhiksha
%+ External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
External Organizations
%T An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised
  Learning : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000C-185A-5
%U https://arxiv.org/abs/2211.11086
%D 2022
%X   Semi-supervised learning (SSL) has shown great promise in leveraging<br>unlabeled data to improve model performance. While standard SSL assumes uniform<br>data distribution, we consider a more realistic and challenging setting called<br>imbalanced SSL, where imbalanced class distributions occur in both labeled and<br>unlabeled data. Although there are existing endeavors to tackle this challenge,<br>their performance degenerates when facing severe imbalance since they can not<br>reduce the class imbalance sufficiently and effectively. In this paper, we<br>study a simple yet overlooked baseline -- SimiS -- which tackles data imbalance<br>by simply supplementing labeled data with pseudo-labels, according to the<br>difference in class distribution from the most frequent class. Such a simple<br>baseline turns out to be highly effective in reducing class imbalance. It<br>outperforms existing methods by a significant margin, e.g., 12.8%, 13.6%, and<br>16.7% over previous SOTA on CIFAR100-LT, FOOD101-LT, and ImageNet127<br>respectively. The reduced imbalance results in faster convergence and better<br>pseudo-label accuracy of SimiS. The simplicity of our method also makes it<br>possible to be combined with other re-balancing techniques to improve the<br>performance further. Moreover, our method shows great robustness to a wide<br>range of data distributions, which holds enormous potential in practice. Code<br>will be publicly available.<br>
%K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Artificial Intelligence, cs.AI,Computer Science, Learning, cs.LG

2021

Conference paper

Y. Fan, A. Kukleva, and B. Schiele

“Revisiting Consistency Regularization for Semi-supervised Learning,” in Pattern Recognition (GCPR 2021), Bonn, Germany, 2022.

@inproceedings{Fan_GCPR2021,
TITLE = {Revisiting Consistency Regularization for Semi-supervised Learning},
AUTHOR = {Fan, Yue and Kukleva, Anna and Schiele, Bernt},
LANGUAGE = {eng},
ISBN = {978-3-030-92659-5; 978-3-030-92658-8},
DOI = {10.1007/978-3-030-92659-5_5},
PUBLISHER = {Springer},
YEAR = {2021},
MARGINALMARK = {$\bullet$},
BOOKTITLE = {Pattern Recognition (GCPR 2021)},
EDITOR = {Bauckhage, Christian and Gall, J{\"u}rgen and Schwing, Alexander},
PAGES = {63--78},
SERIES = {Lecture Notes in Computer Science},
VOLUME = {13024},
ADDRESS = {Bonn, Germany},
}

Endnote

%0 Conference Proceedings
%A Fan, Yue
%A Kukleva, Anna
%A Schiele, Bernt
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Revisiting Consistency Regularization for Semi-supervised Learning : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000C-4358-6
%R 10.1007/978-3-030-92659-5_5
%D 2022
%B 43rd German Conference on Pattern Recognition
%Z date of event: 2021-09-28 - 2021-10-01
%C Bonn, Germany
%B Pattern Recognition
%E Bauckhage, Christian; Gall, J&#252;rgen; Schwing, Alexander
%P 63 - 78
%I Springer
%@ 978-3-030-92659-5 978-3-030-92658-8
%B Lecture Notes in Computer Science
%N 13024

2020

Conference paper

Y. Fan, Y. Xian, M. M. Losch, and B. Schiele

“Analyzing the Dependency of ConvNets on Spatial Information,” in Pattern Recognition (GCPR 2020), Tübingen, Germany, 2021.

@inproceedings{Fan_GCPR2020,
TITLE = {Analyzing the Dependency of {ConvNets} on Spatial Information},
AUTHOR = {Fan, Yue and Xian, Yongqin and Losch, Max Maria and Schiele, Bernt},
LANGUAGE = {eng},
ISBN = {978-3-030-71277-8},
DOI = {10.1007/978-3-030-71278-5_8},
PUBLISHER = {Springer},
YEAR = {2020},
MARGINALMARK = {$\bullet$},
DATE = {2021},
BOOKTITLE = {Pattern Recognition (GCPR 2020)},
EDITOR = {Akata, Zeynep and Geiger, Andreas and Sattler, Torsten},
PAGES = {101--115},
SERIES = {Lecture Notes in Computer Science},
VOLUME = {12544},
ADDRESS = {T{\"u}bingen, Germany},
}

Endnote

%0 Conference Proceedings
%A Fan, Yue
%A Xian, Yongqin
%A Losch, Max Maria
%A Schiele, Bernt
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Analyzing the Dependency of ConvNets on Spatial Information : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0008-3292-A
%R 10.1007/978-3-030-71278-5_8
%D 2021
%B 42nd German Conference on Pattern Recognition
%Z date of event: 2020-09-28 - 2020-10-01
%C T&#252;bingen, Germany
%B Pattern Recognition
%E Akata, Zeynep; Geiger, Andreas; Sattler, Torsten
%P 101 - 115
%I Springer
%@ 978-3-030-71277-8
%B Lecture Notes in Computer Science
%N 12544

Paper

Y. Fan, Y. Xian, M. M. Losch, and B. Schiele

“Analyzing the Dependency of ConvNets on Spatial Information,” 2020. [Online]. Available: https://arxiv.org/abs/2002.01827.

Abstract

Intuitively, image classification should profit from using spatial
information. Recent work, however, suggests that this might be overrated in
standard CNNs. In this paper, we are pushing the envelope and aim to further
investigate the reliance on spatial information. We propose spatial shuffling
and GAP+FC to destroy spatial information during both training and testing
phases. Interestingly, we observe that spatial information can be deleted from
later layers with small performance drops, which indicates spatial information
at later layers is not necessary for good performance. For example, test
accuracy of VGG-16 only drops by 0.03% and 2.66% with spatial information
completely removed from the last 30% and 53% layers on CIFAR100, respectively.
Evaluation on several object recognition datasets (CIFAR100, Small-ImageNet,
ImageNet) with a wide range of CNN architectures (VGG16, ResNet50, ResNet152)
shows an overall consistent pattern.

BibTeX

@online{Fan_arXiv2002.01827,
TITLE = {Analyzing the Dependency of {ConvNets} on Spatial Information},
AUTHOR = {Fan, Yue and Xian, Yongqin and Losch, Max Maria and Schiele, Bernt},
LANGUAGE = {eng},
URL = {https://arxiv.org/abs/2002.01827},
EPRINT = {2002.01827},
EPRINTTYPE = {arXiv},
YEAR = {2020},
ABSTRACT = {Intuitively, image classification should profit from using spatial<br>information. Recent work, however, suggests that this might be overrated in<br>standard CNNs. In this paper, we are pushing the envelope and aim to further<br>investigate the reliance on spatial information. We propose spatial shuffling<br>and GAP+FC to destroy spatial information during both training and testing<br>phases. Interestingly, we observe that spatial information can be deleted from<br>later layers with small performance drops, which indicates spatial information<br>at later layers is not necessary for good performance. For example, test<br>accuracy of VGG-16 only drops by 0.03% and 2.66% with spatial information<br>completely removed from the last 30% and 53% layers on CIFAR100, respectively.<br>Evaluation on several object recognition datasets (CIFAR100, Small-ImageNet,<br>ImageNet) with a wide range of CNN architectures (VGG16, ResNet50, ResNet152)<br>shows an overall consistent pattern.<br>},
}

Endnote

%0 Report
%A Fan, Yue
%A Xian, Yongqin
%A Losch, Max Maria
%A Schiele, Bernt
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Analyzing the Dependency of ConvNets on Spatial Information : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0007-80CB-3
%U https://arxiv.org/abs/2002.01827
%D 2020
%X   Intuitively, image classification should profit from using spatial<br>information. Recent work, however, suggests that this might be overrated in<br>standard CNNs. In this paper, we are pushing the envelope and aim to further<br>investigate the reliance on spatial information. We propose spatial shuffling<br>and GAP+FC to destroy spatial information during both training and testing<br>phases. Interestingly, we observe that spatial information can be deleted from<br>later layers with small performance drops, which indicates spatial information<br>at later layers is not necessary for good performance. For example, test<br>accuracy of VGG-16 only drops by 0.03% and 2.66% with spatial information<br>completely removed from the last 30% and 53% layers on CIFAR100, respectively.<br>Evaluation on several object recognition datasets (CIFAR100, Small-ImageNet,<br>ImageNet) with a wide range of CNN architectures (VGG16, ResNet50, ResNet152)<br>shows an overall consistent pattern.<br>
%K Computer Science, Computer Vision and Pattern Recognition, cs.CV