Yaoyao Liu (PhD Student)

Yaoyao Liu

Adresse
Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
Standort
E1 4 - 624
Telefon
+49 681 9325 2024
Fax
+49 681 9325 2099

Personal Information

Publications

Meta-Transfer Learning through Hard Tasks
Q. Sun, Y. Liu, Z. Chen, T.-S. Chua and B. Schiele
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
(Accepted/in press)
Export
BibTeX
@article{Sun__TPAMI2020, TITLE = {Meta-Transfer Learning through Hard Tasks}, AUTHOR = {Sun, Qianru and Liu, Yaoyao and Chen, Zhaozheng and Chua, Tat-Seng and Schiele, Bernt}, LANGUAGE = {eng}, ISSN = {0162-8828}, DOI = {10.1109/TPAMI.2020.3018506}, PUBLISHER = {IEEE}, ADDRESS = {Piscataway, NJ}, YEAR = {2020}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, JOURNAL = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, }
Endnote
%0 Journal Article %A Sun, Qianru %A Liu, Yaoyao %A Chen, Zhaozheng %A Chua, Tat-Seng %A Schiele, Bernt %+ External Organizations External Organizations External Organizations External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Meta-Transfer Learning through Hard Tasks : %G eng %U http://hdl.handle.net/21.11116/0000-0005-5552-F %R 10.1109/TPAMI.2020.3018506 %D 2020 %J IEEE Transactions on Pattern Analysis and Machine Intelligence %O IEEE Trans. Pattern Anal. Mach. Intell. %I IEEE %C Piscataway, NJ %@ false
An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
Y. Liu, B. Schiele and Q. Sun
Computer Vision -- ECCV 2020, 2020
Export
BibTeX
@inproceedings{Liu_ECCV2020, TITLE = {An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning}, AUTHOR = {Liu, Yaoyao and Schiele, Bernt and Sun, Qianru}, LANGUAGE = {eng}, ISBN = {978-3-030-58516-7}, DOI = {10.1007/978-3-030-58517-4_24}, PUBLISHER = {Springer}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, DATE = {2020}, BOOKTITLE = {Computer Vision -- ECCV 2020}, EDITOR = {Vedaldi, Andrea and Bischof, Horst and Brox, Thomas and Frahm, Jan-Michael}, PAGES = {404--421}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {12361}, ADDRESS = {Glasgow, UK}, }
Endnote
%0 Conference Proceedings %A Liu, Yaoyao %A Schiele, Bernt %A Sun, Qianru %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations %T An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning : %G eng %U http://hdl.handle.net/21.11116/0000-0006-EFBE-8 %R 10.1007/978-3-030-58517-4_24 %D 2020 %B 16th European Conference on Computer Vision %Z date of event: 2020-08-23 - 2020-08-28 %C Glasgow, UK %B Computer Vision -- ECCV 2020 %E Vedaldi, Andrea; Bischof, Horst; Brox, Thomas; Frahm, Jan-Michael %P 404 - 421 %I Springer %@ 978-3-030-58516-7 %B Lecture Notes in Computer Science %N 12361
Mnemonics Training: Multi-Class Incremental Learning Without Forgetting
Y. Liu, Y. Su, A.-A. Liu, B. Schiele and Q. Sun
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), 2020
Export
BibTeX
@inproceedings{Liu_2020_CVPR, TITLE = {Mnemonics Training: {M}ulti-Class Incremental Learning Without Forgetting}, AUTHOR = {Liu, Yaoyao and Su, Yuting and Liu, An-An and Schiele, Bernt and Sun, Qianru}, LANGUAGE = {eng}, ISBN = {978-1-7281-7168-5}, DOI = {10.1109/CVPR42600.2020.01226}, PUBLISHER = {IEEE}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)}, PAGES = {12242--12251}, ADDRESS = {Virtual}, }
Endnote
%0 Conference Proceedings %A Liu, Yaoyao %A Su, Yuting %A Liu, An-An %A Schiele, Bernt %A Sun, Qianru %+ 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 %T Mnemonics Training: Multi-Class Incremental Learning Without Forgetting : %G eng %U http://hdl.handle.net/21.11116/0000-0006-EFD1-1 %R 10.1109/CVPR42600.2020.01226 %D 2020 %B 33rd IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2020-06-14 - 2020-06-19 %C Virtual %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 12242 - 12251 %I IEEE %@ 978-1-7281-7168-5
Learning to Self-Train for Semi-Supervised Few-Shot Classification
X. Li, Q. Sun, Y. Liu, Q. Zhou, S. Zheng, T.-S. Chua and B. Schiele
Advances in Neural Information Processing Systems 32 (NIPS 2019), 2019
Export
BibTeX
@inproceedings{Li_NeurIPs2019, TITLE = {Learning to Self-Train for Semi-Supervised Few-Shot Classification}, AUTHOR = {Li, Xinzhe and Sun, Qianru and Liu, Yaoyao and Zhou, Qin and Zheng, Shibao and Chua, Tat-Seng and Schiele, Bernt}, LANGUAGE = {eng}, URL = {http://papers.nips.cc/paper/9216-learning-to-self-train-for-semi-supervised-few-shot-classification.pdf}, PUBLISHER = {Curran Associates, Inc.}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Advances in Neural Information Processing Systems 32 (NIPS 2019)}, EDITOR = {Wallach, H. and Larochelle, H. and Beygelzimer, A. and d'Alch{\'e}-Buc, F. and Fox, E. and Garnett, R.}, PAGES = {10276--10286}, ADDRESS = {Vancouver, Canada}, }
Endnote
%0 Conference Proceedings %A Li, Xinzhe %A Sun, Qianru %A Liu, Yaoyao %A Zhou, Qin %A Zheng, Shibao %A Chua, Tat-Seng %A Schiele, Bernt %+ External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Learning to Self-Train for Semi-Supervised Few-Shot Classification : %G eng %U http://hdl.handle.net/21.11116/0000-0005-551B-E %U http://papers.nips.cc/paper/9216-learning-to-self-train-for-semi-supervised-few-shot-classification.pdf %D 2019 %B 33rd Conference on Neural Information Processing Systems %Z date of event: 2019-12-08 - 2019-12-14 %C Vancouver, Canada %B Advances in Neural Information Processing Systems 32 %E Wallach, H.; Larochelle, H.; Beygelzimer, A.; d'Alché-Buc, F.; Fox, E.; Garnett, R. %P 10276 - 10286 %I Curran Associates, Inc.
LCC: Learning to Customize and Combine Neural Networks for Few-Shot Learning
Y. Liu, Q. Sun, A.-A. Liu, Y. Su, B. Schiele and T.-S. Chua
Technical Report, 2019
(arXiv: 1904.08479)
Abstract
Meta-learning has been shown to be an effective strategy for few-shot learning. The key idea is to leverage a large number of similar few-shot tasks in order to meta-learn how to best initiate a (single) base-learner for novel few-shot tasks. While meta-learning how to initialize a base-learner has shown promising results, it is well known that hyperparameter settings such as the learning rate and the weighting of the regularization term are important to achieve best performance. We thus propose to also meta-learn these hyperparameters and in fact learn a time- and layer-varying scheme for learning a base-learner on novel tasks. Additionally, we propose to learn not only a single base-learner but an ensemble of several base-learners to obtain more robust results. While ensembles of learners have shown to improve performance in various settings, this is challenging for few-shot learning tasks due to the limited number of training samples. Therefore, our approach also aims to meta-learn how to effectively combine several base-learners. We conduct extensive experiments and report top performance for five-class few-shot recognition tasks on two challenging benchmarks: miniImageNet and Fewshot-CIFAR100 (FC100).
Export
BibTeX
@online{Liu_arXiv1904.08479, TITLE = {{LCC}: {L}earning to Customize and Combine Neural Networks for Few-Shot Learning}, AUTHOR = {Liu, Yaoyao and Sun, Qianru and Liu, An-An and Su, Yuting and Schiele, Bernt and Chua, Tat-Seng}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1904.08479}, EPRINT = {1904.08479}, EPRINTTYPE = {arXiv}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Meta-learning has been shown to be an effective strategy for few-shot learning. The key idea is to leverage a large number of similar few-shot tasks in order to meta-learn how to best initiate a (single) base-learner for novel few-shot tasks. While meta-learning how to initialize a base-learner has shown promising results, it is well known that hyperparameter settings such as the learning rate and the weighting of the regularization term are important to achieve best performance. We thus propose to also meta-learn these hyperparameters and in fact learn a time- and layer-varying scheme for learning a base-learner on novel tasks. Additionally, we propose to learn not only a single base-learner but an ensemble of several base-learners to obtain more robust results. While ensembles of learners have shown to improve performance in various settings, this is challenging for few-shot learning tasks due to the limited number of training samples. Therefore, our approach also aims to meta-learn how to effectively combine several base-learners. We conduct extensive experiments and report top performance for five-class few-shot recognition tasks on two challenging benchmarks: miniImageNet and Fewshot-CIFAR100 (FC100).}, }
Endnote
%0 Report %A Liu, Yaoyao %A Sun, Qianru %A Liu, An-An %A Su, Yuting %A Schiele, Bernt %A Chua, Tat-Seng %+ 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 %T LCC: Learning to Customize and Combine Neural Networks for Few-Shot Learning : %G eng %U http://hdl.handle.net/21.11116/0000-0003-BAF9-3 %U http://arxiv.org/abs/1904.08479 %D 2019 %X Meta-learning has been shown to be an effective strategy for few-shot learning. The key idea is to leverage a large number of similar few-shot tasks in order to meta-learn how to best initiate a (single) base-learner for novel few-shot tasks. While meta-learning how to initialize a base-learner has shown promising results, it is well known that hyperparameter settings such as the learning rate and the weighting of the regularization term are important to achieve best performance. We thus propose to also meta-learn these hyperparameters and in fact learn a time- and layer-varying scheme for learning a base-learner on novel tasks. Additionally, we propose to learn not only a single base-learner but an ensemble of several base-learners to obtain more robust results. While ensembles of learners have shown to improve performance in various settings, this is challenging for few-shot learning tasks due to the limited number of training samples. Therefore, our approach also aims to meta-learn how to effectively combine several base-learners. We conduct extensive experiments and report top performance for five-class few-shot recognition tasks on two challenging benchmarks: miniImageNet and Fewshot-CIFAR100 (FC100). %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Learning, cs.LG,Statistics, Machine Learning, stat.ML
Meta-Transfer Learning for Few-Shot Learning
Q. Sun, Y. Liu, T.-S. Chua and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019
Export
BibTeX
@inproceedings{Sun_CVPR2019, TITLE = {Meta-Transfer Learning for Few-Shot Learning}, AUTHOR = {Sun, Qianru and Liu, Yaoyao and Chua, Tat-Seng and Schiele, Bernt}, LANGUAGE = {eng}, ISBN = {978-1-7281-3293-8}, DOI = {10.1109/CVPR.2019.00049}, PUBLISHER = {IEEE}, YEAR = {2019}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019)}, PAGES = {403--412}, ADDRESS = {Long Beach, CA, USA}, }
Endnote
%0 Conference Proceedings %A Sun, Qianru %A Liu, Yaoyao %A Chua, Tat-Seng %A Schiele, Bernt %+ 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 %T Meta-Transfer Learning for Few-Shot Learning : %G eng %U http://hdl.handle.net/21.11116/0000-0003-9604-F %R 10.1109/CVPR.2019.00049 %D 2019 %B 32nd IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2019-06-16 - 2019-06-20 %C Long Beach, CA, USA %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 403 - 412 %I IEEE %@ 978-1-7281-3293-8