Bias oriented unbiased data augmentation for cross-bias representation learning
Authors: 
Lei Li, Fan Tang, Juan Cao, Xirong Li, 
Danding WangAuthors Info & Claims
Lei Li, Fan Tang, Juan Cao, Xirong Li, Danding WangAuthors Info & ClaimsAbstract
The biased cues in the training data may build strong connections between specific targets and unexpected concepts, leading the learned representations could not be applied to real-world data that does not contain the same biased cues. To learn cross-bias representations which can generalize on unbiased datasets by only using biased data, researchers focus on reducing the influence of biased cues through unbiased sampling or augmentation on the basis of artificial experience. However, the distributions of biased cues in the dataset are neglected, which limits the performance of these methods. In this paper, we propose a bias oriented data augmentation to enhance the cross-bias generalization by enlarging “safety” and “unbiasedness” constraints in the training data without manual prior intervention. The safety constraint is proposed to maintain the class-specific information for augmentation while the unbiasedness constraint reduces the statistical correlation of bias information and class labels. Experiments under different biased proportions on four synthetic/real-world datasets show that the proposed approach could improve the performance of other SOTA debiasing approaches (colored MNIST: 0.35–26.14%, corrupted CIFAR10: 3.14–8.44%, BFFHQ: 1.50% and BAR: 1.72%).
References
[1]
Gaur L, Bhatia U, Jhanjhi N, Muhammad G, and Masud M Medical image-based detection of covid-19 using deep convolution neural networks Multimed. Syst. 2021
[2]
Wei P and Wang B Food image classification and image retrieval based on visual features and machine learning Multimed. Syst. 2020
[3]
Tayal A, Gupta J, Solanki A, Bisht K, Nayyar A, and Masud M Dl-cnn-based approach with image processing techniques for diagnosis of retinal diseases Multimed. Syst. 2021 28 1417-1438
[4]
Ta N, Chen H, Lyu Y, and Wu T Ble-net: boundary learning and enhancement network for polyp segmentation Multimed. Syst. 2022
[5]
Xia K, Gu X, and Zhang Y Oriented grouping-constrained spectral clustering for medical imaging segmentation Multimed. Syst. 2020 26 1 27-36
[6]
Olimov B, Sanjar K, Din S, Ahmad A, Paul A, and Kim J Fu-net: fast biomedical image segmentation model based on bottleneck convolution layers Multimed. Syst. 2021 27 4 637-650
[7]
Poongodi M, Hamdi M, and Wang H Image and audio caps: automated captioning of background sounds and images using deep learning Multimed. Syst. 2022
[8]
Xu N, Liu A-A, Nie W, and Su Y Multi-guiding long short-term memory for video captioning Multimed. Syst. 2019 25 6 663-672
[9]
Shen, Z., Cui, P., Zhang, T., Kunag, K.: Stable learning via sample reweighting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 5692–5699 (2020)
[10]
Nam J, Cha H, Ahn S-S, Lee J, and Shin J Learning from failure: de-biasing classifier from biased classifier Adv. Neural Inf. Process. Syst. 2020 33 20673-20684
[11]
Bahng, H., Chun, S., Yun, S., Choo, J., Oh, S.J.: Learning de-biased representations with biased representations. In: International Conference on Machine Learning, pp. 528–539. PMLR (2020)
[12]
LeCun Y, Bottou L, Bengio Y, and Haffner P Gradient-based learning applied to document recognition Proc. IEEE 1998 86 11 2278-2324
[13]
Bai, H., Sun, R., Hong, L., Zhou, F., Ye, N., Ye, H.-J., Chan, S.-H.G., Li, Z.: Decaug: out-of-distribution generalization via decomposed feature representation and semantic augmentation. arXiv preprint arXiv:2012.09382 (2020)
[14]
Kim, B., Kim, H., Kim, K., Kim, S., Kim, J.: Learning not to learn: training deep neural networks with biased data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9012–9020 (2019)
[15]
Tartaglione, E., Barbano, C.A., Grangetto, M.: End: entangling and disentangling deep representations for bias correction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13508–13517 (2021)
[16]
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=Bygh9j09KX
[17]
Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.-S., Wen, J.-R.: Counterfactual vqa: a cause-effect look at language bias. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12700–12710 (2021)
[18]
Li, Y., Vasconcelos, N.: Repair: removing representation bias by dataset resampling. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9572–9581 (2019)
[19]
Zhang, X., Cui, P., Xu, R., Zhou, L., He, Y., Shen, Z.: Deep stable learning for out-of-distribution generalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5372–5382 (2021)
[20]
Li, L., Gao, K., Cao, J., Huang, Z., Weng, Y., Mi, X., Yu, Z., Li, X., Xia, B.: Progressive domain expansion network for single domain generalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 224–233 (2021)
[21]
Wang, H., He, Z., Lipton, Z.L., Xing, E.P.: Learning robust representations by projecting superficial statistics out. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=rJEjjoR9K7
[22]
Cadene R, Dancette C, Cord M, Parikh D, et al. Rubi: reducing unimodal biases for visual question answering Adv. Neural. Inf. Process. Syst. 2019 32 841-852
[23]
Shorten C and Khoshgoftaar TM A survey on image data augmentation for deep learning J. Big Data 2019 6 1 1-48
[24]
Summers, C., Dinneen, M.J.: Improved mixed-example data augmentation. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1262–1270 (2019). IEEE
[25]
Kang, G., Dong, X., Zheng, L., Yang, Y.: Patchshuffle regularization. arXiv preprint arXiv:1707.07103 (2017)
[26]
Takahashi R, Matsubara T, and Uehara K Data augmentation using random image cropping and patching for deep cnns IEEE Trans. Circuits Syst. Video Technol. 2019 30 9 2917-2931
[27]
DeVries, T., Taylor, G.W.: Dataset augmentation in feature space. arXiv preprint arXiv:1702.05538 (2017)
[28]
Doersch, C.: Tutorial on variational autoencoders. arXiv preprint arXiv:1606.05908 (2016)
[29]
Bowles, C., Chen, L., Guerrero, R., Bentley, P., Gunn, R., Hammers, A., Dickie, D.A., Hernández, M.V., Wardlaw, J., Rueckert, D.: Gan augmentation: augmenting training data using generative adversarial networks. arXiv preprint arXiv:1810.10863 (2018)
[30]
Kortylewski, A., Egger, B., Schneider, A., Gerig, T., Vetter, T.: Analyzing and reducing the damage of dataset bias to face recognition with synthetic data. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2019)
[31]
Jaipuria, N., Zhang, X., Bhasin, R., Arafa, M., Chakravarty, P., Shrivastava, S., Manglani, S., Murali, V.N.: Deflating dataset bias using synthetic data augmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp 772–773 (2020)
[32]
Qian, X., Fu, Y., Tao, X., Wang, W., Xue, X.: Pose-normalized image generation for person re-identification. In: 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, part ix. European Conference on Computer Vision (2018)
[33]
Zhang, X., Tseng, N., Syed, A., Bhasin, R., Jaipuria, N.: Simbar: Single image-based scene relighting for effective data augmentation for automated driving vision tasks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3718–3728 (2022)
[34]
Mao, X., Li, Q., Xie, H., Lau, R., Smolley, S.P.: Least squares generative adversarial networks. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)
[35]
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 214–223. PMLR (2017). https://proceedings.mlr.press/v70/arjovsky17a.html
[36]
Zhang Z and Sabuncu M Generalized cross entropy loss for training deep neural networks with noisy labels Adv. Neural Inf. Process. Syst. 2018 31 8778-8788
[37]
Lee J, Kim E, Lee J, Lee J, and Choo J Learning debiased representation via disentangled feature augmentation Adv. Neural Inf. Process. Syst. 2021 34 25123-25133
[38]
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical Report 0, University of Toronto, Toronto, Ontario (2009)
[39]
Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)
[40]
Kim, E., Lee, J., Choo, J.: Biaswap: Removing dataset bias with bias-tailored swapping augmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 14992–15001 (2021)
[41]
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401–4410 (2019)
[42]
Wang, H., He, Z., Lipton, Z.C., Xing, E.P.: Learning robust representations by projecting superficial statistics out. arXiv preprint arXiv:1903.06256 (2019)
[43]
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Recommendations
Unbiased classification through bias-contrastive and bias-balanced learning
NIPS '21: Proceedings of the 35th International Conference on Neural Information Processing SystemsDatasets for training machine learning models tend to be biased unless the data is collected with complete care. In such a biased dataset, models are susceptible to making predictions based on the biased features of the data. The biased model fails to ...
Data Augmentation for Discrimination Prevention and Bias Disambiguation
AIES '20: Proceedings of the AAAI/ACM Conference on AI, Ethics, and SocietyMachine learning models are prone to biased decisions due to biases in the datasets they are trained on. In this paper, we introduce a novel data augmentation technique to create a fairer dataset for model training that could also lend itself to ...
AmpliBias: Mitigating Dataset Bias through Bias Amplification in Few-shot Learning for Generative Models
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementDeep learning models exhibit a dependency on peripheral attributes of input data, such as shapes and colors, leading the models to become biased towards these certain attributes that result in subsequent degradation of performance. In this paper, we ...
Comments
Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 25 October 2022
Accepted: 08 October 2022
Received: 09 June 2022
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Jan 2025