2020

Explanation-Guided Training for Cross-Domain Few-Shot Classification

Sun, Jiamei, Lapuschkin, Sebastian, Samek, Wojciech et al.

Understand

Cross-domain few-shot classification task (CD-FSC) combines few-shot classification with the requirement to generalize across domains represented by datasets.

This setup faces challenges originating from the limited labeled data in each class and, additionally, from the domain shift between training and test sets.
In this paper, we introduce a novel training approach for existing FSC models.
It leverages on the explanation scores, obtained from existing explanation methods when applied to the predictions of FSC models, computed for intermediate feature maps of the models.

Built on

J. Kauffmann, M. Esders, G. Montavon, W. Samek, and K.-R. Müller, “From clustering to cluster explanations via neural networks,” arXiv:1906.07633
Original
1906
Earlier work this paper cites.
C. Wah, S. Branson, P. Welinder, P. Perona, and S. Belongie, “The caltech-ucsd birds-200-2011 dataset,” 2011
2011
Earlier work this paper cites.
J. Krause, M. Stark, J. Deng, and L. Fei-Fei, “3d object representations for fine-grained categorization,” in Proceedings of the IEEE CVPR workshops , 2013, pp. 554–561
2013
Earlier work this paper cites.
K. Simonyan, A. Vedaldi, and A. Zisserman, “Deep inside convolutional networks: Visualising image classification models and saliency maps,” in ICLR (workshop track) , 2014
2014
Earlier work this paper cites.
S. Bach, A. Binder, G. Montavon, F. Klauschen, K.-R. Müller, and W. Samek, “On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation,” PLOS ONE , vol. 10, no. 7, p. e0130140, 2015
2015
Earlier work this paper cites.
J. Springenberg, A. Dosovitskiy, T. Brox, and M. Riedmiller, “Striving for simplicity: The all convolutional net,” in ICLR (workshop track) , 2015
2015
Earlier work this paper cites.
N. Tishby and N. Zaslavsky, “Deep learning and the information bottleneck principle,” in 2015 IEEE Information Theory Workshop (ITW) . IEEE, 2015, pp. 1–5
2015
Earlier work this paper cites.
O. Vinyals, C. Blundell, T. Lillicrap, D. Wierstra et al. , “Matching networks for one shot learning,” in NIPS , 2016, pp. 3630–3638
2016
Earlier work this paper cites.
M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should i trust you?: Explaining the predictions of any classifier,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . ACM, 2016, pp. 1135–1144
2016
Earlier work this paper cites.
A. Santoro, S. Bartunov, M. Botvinick, D. Wierstra, and T. Lillicrap, “Meta-learning with memory-augmented neural networks,” in ICML , 2016, pp. 1842–1850
2016
Earlier work this paper cites.
O. Vinyals, C. Blundell, T. Lillicrap, D. Wierstra et al. , “Matching networks for one shot learning,” in NIPS , 2016, pp. 3630–3638
2016
Earlier work this paper cites.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE CVPR , 2016, pp. 770–778
2016
Earlier work this paper cites.
C. Finn, P. Abbeel, and S. Levine, “Model-agnostic meta-learning for fast adaptation of deep networks,” in Proceedings of the 34th ICML Volume 70 . JMLR. org, 2017, pp. 1126–1135
2017
Earlier work this paper cites.
J. Snell, K. Swersky, and R. Zemel, “Prototypical networks for few-shot learning,” in NIPS , 2017, pp. 4077–4087
2017
Earlier work this paper cites.
M. Sundararajan, A. Taly, and Q. Yan, “Axiomatic attribution for deep networks,” in Proceedings of the 34th ICML Volume 70 . JMLR. org, 2017, pp. 3319–3328
2017
Earlier work this paper cites.
R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-cam: Visual explanations from deep networks via gradient-based localization,” in Proceedings of the IEEE ICCV , 2017, pp. 618–626
2017
Earlier work this paper cites.
G. Montavon, S. Lapuschkin, A. Binder, W. Samek, and K.-R. Müller, “Explaining nonlinear classification decisions with deep taylor decomposition,” Pattern Recognition , vol. 65, pp. 211–222, 2017
2017
Earlier work this paper cites.
A. Shrikumar, P. Greenside, and A. Kundaje, “Learning important features through propagating activation differences,” in ICML , 2017, pp. 3145–3153
2017
Earlier work this paper cites.
L. Arras, F. Horn, G. Montavon, K.-R. Müller, and W. Samek, ““what is relevant in a text document?”: An interpretable machine learning approach,” PLOS ONE , vol. 12, no. 8, p. e0181142, 2017
2017
Earlier work this paper cites.

Similar

L. Arras, G. Montavon, K.-R. Müller, and W. Samek, “Explaining recurrent neural network predictions in sentiment analysis,” in Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis , 2017, pp. 159–168
2017
Cited alongside, same era.
S. Ravi and H. Larochelle, “Optimization as a model for few-shot learning,” in ICLR , 2017
2017
Cited alongside, same era.
T. Munkhdalai and H. Yu, “Meta networks,” in Proceedings of the 34th ICML Volume 70 , 2017, pp. 2554–2563
2017
Cited alongside, same era.
B. Zhou, A. Lapedriza, A. Khosla, A. Oliva, and A. Torralba, “Places: A 10 million image database for scene recognition,” IEEE TPAMI , vol. 40, no. 6, pp. 1452–1464, 2017
2017
Cited alongside, same era.
F. Sung, Y. Yang, L. Zhang, T. Xiang, P. H. Torr, and T. M. Hospedales, “Learning to compare: Relation network for few-shot learning,” in Proceedings of the IEEE CVPR , 2018, pp. 1199–1208
2018
Cited alongside, same era.
V. G. Satorras and J. B. Estrach, “Few-shot learning with graph neural networks,” in ICLR , 2018
2018
Cited alongside, same era.
P. Kindermans, K. T. Schütt, M. Alber, K.-R. Müller, D. Erhan, B. Kim, and S. Dähne, “Learning how to explain neural networks: Patternnet and patternattribution,” in ICLR , 2018
2018
Cited alongside, same era.
A. Nichol and J. Schulman, “Reptile: a scalable metalearning algorithm,” arXiv preprint arXiv:1803.02999 , vol. 2, no. 3, p. 4, 2018
Original
2018
Cited alongside, same era.
N. Mishra, M. Rohaninejad, X. Chen, and P. Abbeel, “A simple neural attentive meta-learner,” in ICLR , 2018
2018
Cited alongside, same era.
B. Oreshkin, P. R. López, and A. Lacoste, “Tadam: Task dependent adaptive metric for improved few-shot learning,” in NIPS , 2018, pp. 721–731
2018
Cited alongside, same era.
S. Gidaris and N. Komodakis, “Dynamic few-shot visual learning without forgetting,” in Proceedings of the IEEE CVPR , 2018, pp. 4367–4375
2018
Cited alongside, same era.
H. Qi, M. Brown, and D. G. Lowe, “Low-shot learning with imprinted weights,” in Proceedings of the IEEE CVPR , 2018, pp. 5822–5830
2018
Cited alongside, same era.

Then

W.-Y. Chen, Y.-C. Liu, Z. Kira, Y.-C. F. Wang, and J.-B. Huang, “A closer look at few-shot classification,” in ICLR , 2019
2019
Later among the works it cites.
S. Lapuschkin, S. Wäldchen, A. Binder, G. Montavon, W. Samek, and K.-R. Müller, “Unmasking clever hans predictors and assessing what machines really learn,” Nature Communications , vol. 10, no. 1, p. 1096, 2019
2019
Later among the works it cites.
Y. Liu, J. Lee, M. Park, S. Kim, E. Yang, S. Hwang, and Y. Yang, “Learning to propagate labels: transductive propagation network for few-shot learning,” in ICLR , 2019
2019
Later among the works it cites.
S. Gidaris and N. Komodakis, “Generating classification weights with gnn denoising autoencoders for few-shot learning,” in Proceedings of the IEEE CVPR , 2019, pp. 21–30
2019
Later among the works it cites.
C. Xing, N. Rostamzadeh, B. Oreshkin, and P. O. Pinheiro, “Adaptive cross-modal few-shot learning,” in NIPS , 2019, pp. 4848–4858
2019
Later among the works it cites.
X. Li, Q. Sun, Y. Liu, Q. Zhou, S. Zheng, T.-S. Chua, and B. Schiele, “Learning to self-train for semi-supervised few-shot classification,” in NIPS , 2019, pp. 10 276–10 286
2019
Later among the works it cites.
S. Gidaris, A. Bursuc, N. Komodakis, P. Perez, and M. Cord, “Boosting few-shot visual learning with self-supervision,” in Proceedings of the IEEE ICCV , October 2019
2019
Later among the works it cites.
Y. Guo, N. C. Codella, L. Karlinsky, J. R. Smith, T. Rosing, and R. Feris, “A new benchmark for evaluation of cross-domain few-shot learning,” arXiv preprint arXiv:1912.07200 , 2019
Original
2019
Later among the works it cites.
A. M. Saxe, Y. Bansal, J. Dapello, M. Advani, A. Kolchinsky, B. D. Tracey, and D. D. Cox, “On the information bottleneck theory of deep learning,” Journal of Statistical Mechanics: Theory and Experiment , vol. 2019, no. 12, p. 124020, 2019
2019
Later among the works it cites.
H.-Y. Tseng, H.-Y. Lee, J.-B. Huang, and M.-H. Yang, “Cross-domain few-shot classification via learned feature-wise transformation,” in ICLR , 2020
2020
Closest in time.
B. Liu, Z. Zhao, Z. Li, J. Jiang, Y. Guo, H. Shen, and J. Ye, “Feature transformation ensemble model with batch spectral regularization for cross-domain few-shot classification,” arXiv preprint arXiv:2005.08463 , 2020
Original
2020
Closest in time.
J.-F. Yeh, H.-Y. Lee, B.-C. Tsai, Y.-R. Chen, P.-C. Huang, and W. H. Hsu, “Large margin mechanism and pseudo query set on cross-domain few-shot learning,” arXiv preprint arXiv:2005.09218 , 2020
Original
2020
Closest in time.
T. Schnake, O. Eberle, J. Lederer, S. Nakajima, K. T. Schütt, K.-R. Müller, and G. Montavon, “XAI for Graphs: Explaining graph neural network predictions by identifying relevant walks,” arXiv preprint arXiv:2006.03589 , 2020
Original
2020
Closest in time.
A. Devos and M. Grossglauser, “Regression networks for meta-learning few-shot classification,” 7th ICML Workshop on Automated Machine Learning , 2020
2020
Closest in time.
P. Bateni, R. Goyal, V. Masrani, F. Wood, and L. Sigal, “Improved few-shot visual classification,” in Proceedings of the IEEE CVPR , 2020, pp. 14 493–14 502
2020
Closest in time.
A. Li, W. Huang, X. Lan, J. Feng, Z. Li, and L. Wang, “Boosting few-shot learning with adaptive margin loss,” in Proceedings of the IEEE CVPR , 2020, pp. 12 576–12 584
2020
Closest in time.
J. Cai and S. M. Shen, “Cross-domain few-shot learning with meta fine-tuning,” arXiv preprint arXiv:2005.10544 , 2020
Original
2020
Closest in time.
M. Kohlbrenner, A. Bauer, S. Nakajima, A. Binder, W. Samek, and S. Lapuschkin, “Towards best practice in explaining neural network decisions with LRP,” in IJCNN , 2020, pp. 1–7
2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…