Papers
Topics
Authors
Recent
Search
2000 character limit reached

A Parameterized Generative Adversarial Network Using Cyclic Projection for Explainable Medical Image Classification

Published 24 Nov 2023 in cs.CV and cs.LG | (2311.14388v3)

Abstract: Although current data augmentation methods are successful to alleviate the data insufficiency, conventional augmentation are primarily intra-domain while advanced generative adversarial networks (GANs) generate images remaining uncertain, particularly in small-scale datasets. In this paper, we propose a parameterized GAN (ParaGAN) that effectively controls the changes of synthetic samples among domains and highlights the attention regions for downstream classification. Specifically, ParaGAN incorporates projection distance parameters in cyclic projection and projects the source images to the decision boundary to obtain the class-difference maps. Our experiments show that ParaGAN can consistently outperform the existing augmentation methods with explainable classification on two small-scale medical datasets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. Laith Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J. Big Data, vol. 8, no. 1, pp. 53, 2021.
  2. Nitish Srivastava et al., “Dropout: a simple way to prevent neural networks from overfitting,” J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929–1958, 2014.
  3. Sergey Ioffe et al., “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in Proc. Int. Conf. on Mach. Learn., 2015, vol. 37, pp. 448–456.
  4. Lei Jimmy Ba et al., “Layer normalization,” CoRR, vol. abs/1607.06450, 2016.
  5. Yuxin Wu et al., “Group normalization,” in Proc. Eur. Conf. on Comput. Vis., 2018, vol. 11217, pp. 3–19.
  6. Alex Krizhevsky et al., “Imagenet classification with deep convolutional neural networks,” in Proc. Adv. Neural Inf. Process. Syst., 2012, pp. 1106–1114.
  7. Dan C. Ciresan et al., “High-performance neural networks for visual object classification,” CoRR, vol. abs/1102.0183, 2011.
  8. Ian J. Goodfellow et al., “Generative adversarial nets,” in Proc. Adv. Neural Inf. Process. Syst., 2014, pp. 2672–2680.
  9. Alec Radford et al., “Unsupervised representation learning with deep convolutional generative adversarial networks,” in Proc. Int. Conf. on Learn. Represent., 2016.
  10. M Frid-Adar et al., “Synthetic data augmentation using GAN for improved liver lesion classification,” in Proc. IEEE Int. Symp. Biomed. Imaging, 2018, pp. 289–293.
  11. Shih-Kai Hung et al., “Augmentation of small training data using gans for enhancing the performance of image classification,” in Prof. Int. Conf. on Pattern Recognit., 2020, pp. 3350–3356.
  12. Divya Saxena et al., “Generative adversarial networks (gans): Challenges, solutions, and future directions,” ACM Comput. Surv., vol. 54, no. 3, pp. 63:1–63:42, 2022.
  13. Hongjiang Shi et al., “Data augmentation with improved generative adversarial networks,” in Prof. Int. Conf. on Pattern Recognit., 2018, pp. 73–78.
  14. Ayaan Haque, “EC-GAN: low-sample classification using semi-supervised algorithms and gans (student abstract),” in Proc. AAAI Conf. Artif. Intell., 2021, pp. 15797–15798.
  15. Mehdi Mirza et al., “Conditional generative adversarial nets,” CoRR, vol. abs/1411.1784, 2014.
  16. Augustus Odena et al., “Conditional image synthesis with auxiliary classifier gans,” in Proc. Int. Conf. on Mach. Learn., 2017, vol. 70, pp. 2642–2651.
  17. Shabab Bazrafkan et al., “Versatile auxiliary classifier with generative adversarial network (vac+gan), multi class scenarios,” CoRR, vol. abs/1806.07751, 2018.
  18. Yongyi Lu et al., “Attribute-guided face generation using conditional cyclegan,” in Proc. Eur. Conf. on Comput. Vis., 2018, vol. 11216, pp. 293–308.
  19. Daichi Horita et al., “Food category transfer with conditional cyclegan and a large-scale food image dataset,” in Proc. CEA/MADiMa@IJCAI, 2018, pp. 67–70.
  20. Yunjey Choi et al., “Stargan: Unified generative adversarial networks for multi-domain image-to-image translation,” in Proc. IEEE Int. Conf. on Comput. Vis. and Pattern Recognit., 2018, pp. 8789–8797.
  21. Ramprasaath 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.
  22. Walid Al-Dhabyani et al., “Dataset of breast ultrasound images,” Data in Brief, vol. 28, pp. 104863, 2020.
  23. Moi Hoon Yap et al., “Automated breast ultrasound lesions detection using convolutional neural networks,” IEEE J. Biomed. Health. Inf., vol. 22, no. 4, pp. 1218–1226, 2018.
  24. Zhao et al., “Covid-ct-dataset: a ct scan dataset about covid-19,” arXiv preprint arXiv:2003.13865, 2020.
  25. Junyan Zhu et al., “Unpaired image-to-image translation using cycle-consistent adversarial networks,” in Proc. IEEE Int. Conf. on Comput. Vis., 2017, pp. 2242–2251.
  26. Phillip Isola et al., “Image-to-image translation with conditional adversarial networks,” in Proc. IEEE Int. Conf. on Comput. Vis. and Pattern Recognit., 2017, pp. 5967–5976.
  27. Zhuang Liu et al., “A convnet for the 2020s,” in Proc. IEEE Int. Conf. on Comput. Vis. and Pattern Recognit., 2022, pp. 11966–11976.
  28. Van der Maaten et al., “Visualizing data using t-sne.,” J Mach Learn Res, vol. 9, no. 11, 2008.
Citations (4)
View on Semantic Scholar

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