Papers
Topics
Authors
Recent
Search
2000 character limit reached

Distance Guided Generative Adversarial Network for Explainable Binary Classifications

Published 29 Dec 2023 in cs.CV, cs.LG, and eess.IV | (2312.17538v1)

Abstract: Despite the potential benefits of data augmentation for mitigating the data insufficiency, traditional augmentation methods primarily rely on the prior intra-domain knowledge. On the other hand, advanced generative adversarial networks (GANs) generate inter-domain samples with limited variety. These previous methods make limited contributions to describing the decision boundaries for binary classification. In this paper, we propose a distance guided GAN (DisGAN) which controls the variation degrees of generated samples in the hyperplane space. Specifically, we instantiate the idea of DisGAN by combining two ways. The first way is vertical distance GAN (VerDisGAN) where the inter-domain generation is conditioned on the vertical distances. The second way is horizontal distance GAN (HorDisGAN) where the intra-domain generation is conditioned on the horizontal distances. Furthermore, VerDisGAN can produce the class-specific regions by mapping the source images to the hyperplane. Experimental results show that DisGAN consistently outperforms the GAN-based augmentation methods with explainable binary classification. The proposed method can apply to different classification architectures and has potential to extend to multi-class classification.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (54)
  1. L. Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J. Big Data, vol. 8, no. 1, p. 53, 2021.
  2. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” in Proc. Adv. Neural Inf. Process. Syst., 2012, pp. 1106–1114.
  3. J. Redmon, S. K. Divvala, R. B. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proc. IEEE Int. Conf. on Comput. Vis. and Pattern Recognit.   IEEE Computer Society, 2016, pp. 779–788.
  4. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Proc. Int. Conf. Med. Image Comput. Comput.-Assisted Intervention, vol. 9351.   Springer, 2015, pp. 234–241.
  5. G. Balakrishnan, A. Zhao, M. R. Sabuncu, J. V. Guttag, and A. V. Dalca, “Voxelmorph: A learning framework for deformable medical image registration,” IEEE Trans. Medical Imaging, vol. 38, no. 8, pp. 1788–1800, 2019.
  6. N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: a simple way to prevent neural networks from overfitting,” J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929–1958, 2014.
  7. S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in Proc. Int. Conf. on Mach. Learn., vol. 37, 2015, pp. 448–456.
  8. L. J. Ba, J. R. Kiros, and G. E. Hinton, “Layer normalization,” CoRR, vol. abs/1607.06450, 2016. [Online]. Available: http://arxiv.org/abs/1607.06450
  9. Y. Wu and K. He, “Group normalization,” in Proc. Eur. Conf. on Comput. Vis., vol. 11217.   Springer, 2018, pp. 3–19.
  10. D. C. Ciresan, U. Meier, J. Masci, L. M. Gambardella, and J. Schmidhuber, “High-performance neural networks for visual object classification,” CoRR, vol. abs/1102.0183, 2011.
  11. T. DeVries and G. W. Taylor, “Dataset augmentation in feature space,” in 5th International Conference on Learning Representations, ICLR 2017.   OpenReview.net, 2017. [Online]. Available: https://openreview.net/forum?id=HyaF53XYx
  12. H. Zhang, M. Cissé, Y. N. Dauphin, and D. Lopez-Paz, “mixup: Beyond empirical risk minimization,” in 6th International Conference on Learning Representations, ICLR 2018.   OpenReview.net, 2018. [Online]. Available: https://openreview.net/forum?id=r1Ddp1-Rb
  13. I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. C. Courville, and Y. Bengio, “Generative adversarial nets,” in Proc. Adv. Neural Inf. Process. Syst., 2014, pp. 2672–2680.
  14. D. Saxena and J. Cao, “Generative adversarial networks (gans): Challenges, solutions, and future directions,” ACM Comput. Surv., vol. 54, no. 3, pp. 63:1–63:42, 2022.
  15. L. Rosasco, E. D. Vito, A. Caponnetto, M. Piana, and A. Verri, “Are Loss Functions All the Same?” Neural Computation, vol. 16, no. 5, pp. 1063–1076, 05 2004.
  16. R. R. Selvaraju et al., “Grad-cam: Visual explanations from deep networks via gradient-based localization,” in Proc. IEEE Int. Conf. on Comput. Vis., 2017, pp. 618–626. [Online]. Available: https://doi.org/10.1109/ICCV.2017.74
  17. P. Isola, J. Zhu, T. Zhou, and A. A. Efros, “Image-to-image translation with conditional adversarial networks,” in Proc. IEEE Int. Conf. on Comput. Vis. and Pattern Recognit.   IEEE Computer Society, 2017, pp. 5967–5976.
  18. M. Liu, T. M. Breuel, and J. Kautz, “Unsupervised image-to-image translation networks,” in Proc. Adv. Neural Inf. Process. Syst., 2017, pp. 700–708.
  19. J. Zhu, T. Park, P. Isola, and A. A. Efros, “Unpaired image-to-image translation using cycle-consistent adversarial networks,” in Proc. IEEE Int. Conf. on Comput. Vis.   IEEE Computer Society, 2017, pp. 2242–2251.
  20. T. Kim, M. Cha, H. Kim, J. K. Lee, and J. Kim, “Learning to discover cross-domain relations with generative adversarial networks,” in Proc. Int. Conf. on Mach. Learn., vol. 70.   PMLR, 2017, pp. 1857–1865.
  21. A. Radford, L. Metz, and S. Chintala, “Unsupervised representation learning with deep convolutional generative adversarial networks,” in Proc. Int. Conf. on Learn. Represent., 2016.
  22. M. Frid-Adar, E. Klang, M. Amitai, J. Goldberger, and H. Greenspan, “Synthetic data augmentation using GAN for improved liver lesion classification,” in 15th IEEE International Symposium on Biomedical Imaging, ISBI.   IEEE, 2018, pp. 289–293.
  23. H. Shi, L. Wang, G. Ding, F. Yang, and X. Li, “Data augmentation with improved generative adversarial networks,” in 24th International Conference on Pattern Recognition, ICPR 2018, Beijing, China, August 20-24, 2018.   IEEE Computer Society, 2018, pp. 73–78.
  24. A. Haque, “EC-GAN: low-sample classification using semi-supervised algorithms and gans (student abstract),” in Proc. AAAI Conf. Artif. Intell.   AAAI Press, 2021, pp. 15 797–15 798.
  25. Y. Chen, Y. Zhu, and Y. Chang, “Cyclegan based data augmentation for melanoma images classification,” in AIPR 2020: 3rd International Conference on Artificial Intelligence and Pattern Recognition.   ACM, 2020, pp. 115–119.
  26. Q. H. Cap, H. Uga, S. Kagiwada, and H. Iyatomi, “Leafgan: An effective data augmentation method for practical plant disease diagnosis,” IEEE Trans Autom. Sci. Eng., vol. 19, no. 2, pp. 1258–1267, 2022.
  27. G. Bargshady, X. Zhou, P. D. Barua, R. Gururajan, Y. Li, and U. R. Acharya, “Application of cyclegan and transfer learning techniques for automated detection of COVID-19 using x-ray images,” Pattern Recognit. Lett., vol. 153, pp. 67–74, 2022.
  28. M. Mirza and S. Osindero, “Conditional generative adversarial nets,” CoRR, vol. abs/1411.1784, 2014. [Online]. Available: http://arxiv.org/abs/1411.1784
  29. A. Odena, “Semi-supervised learning with generative adversarial networks,” CoRR, vol. abs/1606.01583, 2016. [Online]. Available: http://arxiv.org/abs/1606.01583
  30. A. Odena, C. Olah, and J. Shlens, “Conditional image synthesis with auxiliary classifier gans,” in Proc. Int. Conf. on Mach. Learn., vol. 70.   PMLR, 2017, pp. 2642–2651.
  31. S. Bazrafkan and P. Corcoran, “Versatile auxiliary classifier with generative adversarial network (vac+gan), multi class scenarios,” CoRR, vol. abs/1806.07751, 2018. [Online]. Available: http://arxiv.org/abs/1806.07751
  32. Y. Lu, Y. Tai, and C. Tang, “Attribute-guided face generation using conditional cyclegan,” in Proc. Eur. Conf. on Comput. Vis., vol. 11216.   Springer, 2018, pp. 293–308.
  33. D. Horita, R. Tanno, W. Shimoda, and K. Yanai, “Food category transfer with conditional cyclegan and a large-scale food image dataset,” in Proceedings of the Joint Workshop on Multimedia for Cooking and Eating Activities and Multimedia Assisted Dietary Management, MADiMa@IJCAI.   ACM, 2018, pp. 67–70.
  34. Y. Choi, M. Choi, M. Kim, J. Ha, S. Kim, and J. Choo, “Stargan: Unified generative adversarial networks for multi-domain image-to-image translation,” in Proc. IEEE Int. Conf. on Comput. Vis. and Pattern Recognit.   Computer Vision Foundation / IEEE Computer Society, 2018, pp. 8789–8797.
  35. X. Xiong, Y. Sun, X. Liu, C. Lam, T. Tong, H. Chen, Q. Gao, W. Ke, and T. Tan, “A parameterized generative adversarial network using cyclic projection for explainable medical image classification,” CoRR, vol. abs/2311.14388, 2023. [Online]. Available: https://doi.org/10.48550/arXiv.2311.14388
  36. X. Mao, Q. Li, H. Xie, R. Y. K. Lau, Z. Wang, and S. P. Smolley, “Least squares generative adversarial networks,” in Proc. IEEE Int. Conf. on Comput. Vis.   IEEE Computer Society, 2017, pp. 2813–2821.
  37. J. Johnson, A. Alahi, and L. Fei-Fei, “Perceptual losses for real-time style transfer and super-resolution,” in Proc. Eur. Conf. on Comput. Vis., Springer.   Springer, 2016, pp. 694–711.
  38. D. Ulyanov, A. Vedaldi, and V. S. Lempitsky, “Instance normalization: The missing ingredient for fast stylization,” CoRR, vol. abs/1607.08022, 2016. [Online]. Available: http://arxiv.org/abs/1607.08022
  39. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in Proc. Int. Conf. on Learn. Represent., 2015.
  40. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. E. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” in Proc. IEEE Int. Conf. on Comput. Vis. and Pattern Recognit.   IEEE Computer Society, 2015, pp. 1–9.
  41. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Int. Conf. on Comput. Vis. and Pattern Recognit.   IEEE Computer Society, 2016, pp. 770–778.
  42. G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proc. IEEE Int. Conf. on Comput. Vis. and Pattern Recognit.   IEEE Computer Society, 2017, pp. 2261–2269.
  43. M. Tan et al., “Mnasnet: Platform-aware neural architecture search for mobile,” in Proc. IEEE Int. Conf. on Comput. Vis. and Pattern Recognit.   Computer Vision Foundation / IEEE, 2019, pp. 2820–2828.
  44. M. Tan and Q. V. Le, “Efficientnet: Rethinking model scaling for convolutional neural networks,” in Proc. Int. Conf. on Mach. Learn., vol. 97.   PMLR, 2019, pp. 6105–6114.
  45. Z. Liu, H. Mao, C. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, “A convnet for the 2020s,” in Proc. IEEE Int. Conf. on Comput. Vis. and Pattern Recognit.   IEEE, 2022, pp. 11 966–11 976.
  46. KeithPinson, “Yum or yuck butterfly mimics 2022,” 2022. [Online]. Available: https://kaggle.com/competitions/yum-or-yuck-butterfly-mimics-2022
  47. S. Goumiri, D. Benboudjema, and W. Pieczynski, “A new hybrid model of convolutional neural networks and hidden markov chains for image classification,” Neural Comput. Appl., vol. 35, no. 24, pp. 17 987–18 002, 2023.
  48. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014. [Online]. Available: https://arxiv.org/abs/1412.6980
  49. J. Deng, W. Dong, R. Socher, L. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in Proc. IEEE Int. Conf. on Comput. Vis. and Pattern Recognit.   IEEE Computer Society, 2009, pp. 248–255.
  50. Y. Zhang, W. Deng, and L. Zheng, “Unsupervised evaluation of out-of-distribution detection: A data-centric perspective,” CoRR, vol. abs/2302.08287, 2023. [Online]. Available: https://doi.org/10.48550/arXiv.2302.08287
  51. W. Al-Dhabyani, M. Gomaa, H. Khaled, and A. Fahmy, “Dataset of breast ultrasound images,” Data in Brief, vol. 28, p. 104863, 2020.
  52. M. H. Yap et al., “Automated breast ultrasound lesions detection using convolutional neural networks,” IEEE J. Biomed. Health Informatics, vol. 22, no. 4, pp. 1218–1226, 2018.
  53. J. Zhao, Y. Zhang, X. He, and P. Xie, “Covid-ct-dataset: a ct scan dataset about covid-19,” arXiv preprint arXiv:2003.13865, 2020. [Online]. Available: https://arxiv.org/abs/2003.13865
  54. L. Van der Maaten and G. Hinton, “Visualizing data using t-sne.” Journal of machine learning research, vol. 9, no. 11, 2008.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now