Papers
Topics
Authors
Recent
Search
2000 character limit reached

Learning Instance-Specific Parameters of Black-Box Models Using Differentiable Surrogates

Published 23 Jul 2024 in cs.CV | (2407.17530v2)

Abstract: Tuning parameters of a non-differentiable or black-box compute is challenging. Existing methods rely mostly on random sampling or grid sampling from the parameter space. Further, with all the current methods, it is not possible to supply any input specific parameters to the black-box. To the best of our knowledge, for the first time, we are able to learn input-specific parameters for a black box in this work. As a test application, we choose a popular image denoising method BM3D as our black-box compute. Then, we use a differentiable surrogate model (a neural network) to approximate the black-box behaviour. Next, another neural network is used in an end-to-end fashion to learn input instance-specific parameters for the black-box. Motivated by prior advances in surrogate-based optimization, we applied our method to the Smartphone Image Denoising Dataset (SIDD) and the Color Berkeley Segmentation Dataset (CBSD68) for image denoising. The results are compelling, demonstrating a significant increase in PSNR and a notable improvement in SSIM nearing 0.93. Experimental results underscore the effectiveness of our approach in achieving substantial improvements in both model performance and optimization efficiency. For code and implementation details, please refer to our GitHub repository: https://github.com/arnisha-k/instance-specific-param

Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. A high-quality denoising dataset for smartphone cameras. In IEEE Conference on Computer Vision and Pattern Recognition, pages 1692–1700. IEEE, 2018.
  2. Autosimulate: (quickly) learning synthetic data generation. In 16th European Conference on Computer Vision (ECCV), 2020.
  3. Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13(Feb):281–305, 2012.
  4. Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms. In 12th Python in Science Conference, pages 13–20. Citeseer, 2013.
  5. Image preprocessing for improving ocr accuracy. In 2007 International Conference on Perspective Technologies and Methods in MEMS Design, pages 75–80. IEEE, 2007.
  6. Learning to learn for global optimization of black box functions. arXiv, 2016.
  7. Image denoising by sparse 3-d transform-domain collaborative filtering. IEEE Transactions on Image Processing, 16(8):2080–2095, 2007.
  8. An image is worth 16x16 words: Transformers for image recognition at scale. CoRR, abs/2010.11929, 2020.
  9. Image denoising via sparse and redundant representations over learned dictionaries. IEEE Transactions on Image Processing, 15(12):3736–3745, 2006.
  10. Toward convolutional blind denoising of real photographs. arXiv preprint arXiv:1807.04686, 2018.
  11. Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (cma-es). Evolutionary Computation, 11(1):1–18, 2003.
  12. Unetr: Transformers for 3d medical image segmentation, 2021.
  13. Deepotsu: Document enhancement and binarization using iterative deep learning. Pattern Recognition, 91:379–390, 7 2019.
  14. Icdar2019 competition on scanned receipt ocr and information extraction. In 2019 International Conference on Document Analysis and Recognition (ICDAR), pages 1516–1520, 2019.
  15. Synthetic data and artificial neural networks for natural scene text recognition. In Workshop on Deep Learning, NIPS, 2014.
  16. An evaluation of parallel thinning algorithms for character recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17:914–919, 1995.
  17. A review of design optimization methods for electrical machines. Energies, 10:1962, 11 2017.
  18. Limited-memory matrix adaptation for large scale black-box optimization. CoRR, abs/1705.06693, 2017.
  19. Bayesian approach to global optimization. Springer, 2(1):2–3, 1975.
  20. Monte carlo gradient estimation in machine learning. arXiv preprint arXiv:1906.10652, 2019.
  21. A simplex method for function minimization. The Computer Journal, 7(4):308–313, 1965.
  22. Numerical optimization. Springer Science & Business Media, 2006.
  23. Nobuyuki Otsu. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9:62–66, 1979.
  24. Principles of Optimal Design: Modeling and Computation. Cambridge University Press, 2000.
  25. MJD Powell. A method for minimizing a sum of squares of non-linear functions without calculating derivatives. Computational Journal, 7(4):303–307, 1965.
  26. William K. Pratt. Digital Image Processing. Wiley-Interscience, 1st edition, 1974.
  27. Unknown-box approximation to improve optical character recognition performance. CoRR, abs/2105.07983, 2021.
  28. Playing for data: Ground truth from computer games. In European Conference on Computer Vision, pages 102–118. Springer, 2016.
  29. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), volume 9351 of LNCS, pages 234–241. Springer, 2015. (available on arXiv:1505.04597 [cs.CV]).
  30. The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3234–3243, 2016.
  31. Learning to simulate. In International Conference on Learning Representations, 2019.
  32. Taking the human out of the loop: A review of bayesian optimization. IEEE, 104(1):148–175, 2016.
  33. Differentiating the black-box: Optimization with local generative surrogates. CoRR, abs/2002.04632, 2020.
  34. Practical bayesian optimization of machine learning algorithms. In Advances in Neural Information Processing Systems, pages 2004–2012, 2012.
  35. Policy improvement: Between black-box optimization and episodic reinforcement learning. Technical report, Technical Report hal-00738463, 2013.
  36. Multi-task bayesian optimization. In Advances in Neural Information Processing Systems, 2013.
  37. Hyperparameter optimization in black-box image processing using differentiable proxies. ACM Transactions on Graphics (TOG), 38(4), 7 2019.
  38. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4):600–612, 2004.
  39. Ronald J. Williams. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3-4):229–256, May 1992.
  40. Ronald J Williams. Simple statistical gradient-following algorithms for connectionist reinforcement learning. In Reinforcement Learning, pages 5–32. Springer, 1992.

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

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free