Abstract
Training of generative models especially Generative Adversarial Networks can easily diverge in low-data setting. To mitigate this issue, we propose a novel implicit data augmentation approach which facilitates stable training and synthesize high-quality samples without need of label information. Specifically, we view the discriminator as a metric embedding of the real data manifold, which offers proper distances between real data points. We then utilize information in the feature space to develop a fully unsupervised and data-driven augmentation method. Experiments on few-shot generation tasks show the proposed method significantly improve results from strong baselines with hundreds of training samples.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arandjelović, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2911–2918. IEEE (2012)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 214–223. PMLR (2017)
Balestriero, R., Pesenti, J., LeCun, Y.: Learning in high dimension always amounts to extrapolation (2021)
Bińkowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. In: International Conference on Learning Representations (2018)
Choe, J., Park, S., Kim, K., Hyun Park, J., Kim, D., Shim, H.: Face generation for low-shot learning using generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops (2017)
Chum, O., Mikulik, A., Perdoch, M., Matas, J.: Total recall II: query expansion revisited. In: CVPR 2011, pp. 889–896. IEEE (2011)
Chum, O., Philbin, J., Sivic, J., Isard, M., Zisserman, A.: Total recall: automatic query expansion with a generative feature model for object retrieval. In: 2007 IEEE 11th International Conference on Computer Vision, pp. 1–8. IEEE (2007)
Dai, M., Hang, H.: Manifold matching via deep metric learning for generative modeling. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 6587–6597 (2021)
Dai, M., Hang, H., Srivastava, A.: Rethinking multidimensional discriminator output for generative adversarial networks (2021)
DeVries, T., Taylor, G.W.: Dataset augmentation in feature space. arXiv preprint arXiv:1702.05538 (2017)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Hong, J., et al.: Reinforced attention for few-shot learning and beyond. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 913–923 (2021)
Hong, Y., Niu, L., Zhang, J., Liang, J., Zhang, L.: DeltaGAN: towards diverse few-shot image generation with sample-specific delta. arXiv preprint arXiv:2009.08753 (2020)
Hong, Y., Niu, L., Zhang, J., Zhao, W., Fu, C., Zhang, L.: F2GAN: fusing-and-filling GAN for few-shot image generation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2535–2543 (2020)
Huang, K., Geng, J., Jiang, W., Deng, X., Xu, Z.: Pseudo-loss confidence metric for semi-supervised few-shot learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 8671–8680 (2021)
Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. In: Proceedings of the NeurIPS (2020)
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: Proceedings of the CVPR (2020)
Kim, J.H., Choo, W., Song, H.O.: Puzzle mix: exploiting saliency and local statistics for optimal mixup. In: International Conference on Machine Learning (ICML) (2020)
Kim, J., Choo, W., Jeong, H., Song, H.O.: Co-mixup: saliency guided joint mixup with supermodular diversity. In: International Conference on Learning Representations (2021)
Ko, B., Gu, G.: Embedding expansion: augmentation in embedding space for deep metric learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)
Krizhevsky, A., Nair, V., Hinton, G.: CIFAR-10 (Canadian institute for advanced research)
Li, Y., Zhang, R., Lu, J., Shechtman, E.: Few-shot image generation with elastic weight consolidation. arXiv preprint arXiv:2012.02780 (2020)
Li, Y., et al.: Few-shot object detection via classification refinement and distractor retreatment. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15395–15403 (2021)
Lim, J.H., Ye, J.C.: Geometric GAN (2017)
Liu, B., Zhu, Y., Song, K., Elgammal, A.: Towards faster and stabilized GAN training for high-fidelity few-shot image synthesis. In: International Conference on Learning Representations (2021)
Liu, S., Wang, Y.: Few-shot learning with online self-distillation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, pp. 1067–1070 (2021)
Ojha, U., et al.: Few-shot image generation via cross-domain correspondence. In: CVPR (2021)
Sajjadi, M.S.M., Bachem, O., Lučić, M., Bousquet, O., Gelly, S.: Assessing generative models via precision and recall. In: Advances in Neural Information Processing Systems (NeurIPS) (2018)
Shao, H., Kumar, A., Thomas Fletcher, P.: The Riemannian geometry of deep generative models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2018)
Si, Z., Zhu, S.C.: Learning hybrid image templates (hit) by information projection. IEEE Trans. Pattern Anal. Mach. Intell. 34, 1354–1367 (2012)
Stojanov, S., Thai, A., Rehg, J.M.: Using shape to categorize: low-shot learning with an explicit shape bias. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1798–1808 (2021)
Thulasidasan, S., Chennupati, G., Bilmes, J.A., Bhattacharya, T., Michalak, S.: On mixup training: improved calibration and predictive uncertainty for deep neural networks. In: Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)
Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J.B., Isola, P.: Rethinking few-shot image classification: a good embedding is all you need? arXiv abs/2003.11539 (2020)
Tseng, H.Y., Jiang, L., Liu, C., Yang, M.H., Yang, W.: Regularing generative adversarial networks under limited data. In: CVPR (2021)
Turcot, P., Lowe, D.G.: Better matching with fewer features: the selection of useful features in large database recognition problems. In: 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, pp. 2109–2116. IEEE (2009)
Verma, V., et al.: Manifold mixup: better representations by interpolating hidden states. In: International Conference on Machine Learning, pp. 6438–6447. PMLR (2019)
Yao, H., et al.: Automated relational meta-learning. In: International Conference on Learning Representations (2020)
Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019)
Zhang, C., Song, N., Lin, G., Zheng, Y., Pan, P., Xu, Y.: Few-shot incremental learning with continually evolved classifiers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12455–12464 (2021)
Zhang, H., Zhang, Z., Odena, A., Lee, H.: Consistency regularization for generative adversarial networks. In: International Conference on Learning Representations (2020)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=r1Ddp1-Rb
Zhao, S., Liu, Z., Lin, J., Zhu, J.Y., Han, S.: Differentiable augmentation for data-efficient GAN training. In: Conference on Neural Information Processing Systems (NeurIPS) (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dai, M., Hang, H., Guo, X. (2022). Adaptive Feature Interpolation for Low-Shot Image Generation. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13675. Springer, Cham. https://doi.org/10.1007/978-3-031-19784-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-19784-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19783-3
Online ISBN: 978-3-031-19784-0
eBook Packages: Computer ScienceComputer Science (R0)