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

翻译：调整不可微分或黑盒计算模型的参数具有挑战性。现有方法主要依赖于从参数空间进行随机采样或网格采样。此外，当前所有方法均无法向黑盒模型提供输入特定的参数。据我们所知，本研究首次实现了对黑盒模型输入特定参数的学习。作为测试应用，我们选择流行的图像去噪方法BM3D作为黑盒计算模型。随后，我们使用可微分代理模型（神经网络）来近似黑盒行为。接着，以端到端方式训练另一个神经网络来学习黑盒的输入实例特定参数。受基于代理的优化方法先前进展的启发，我们将本方法应用于智能手机图像去噪数据集（SIDD）和彩色伯克利分割数据集（CBSD68）进行图像去噪实验。结果令人信服，PSNR显著提升，SSIM指标接近0.93的显著改善。实验结果证实了本方法在提升模型性能和优化效率方面的有效性。代码与实现细节请访问GitHub仓库：https://github.com/arnisha-k/instance-specific-param