用延续法优化展开网络初始值，提升压缩感知重建效果。
How to warm-start your unfolding network
- 结合延续法暖启动展开网络关键参数。
- 在真实图像上实现更平滑的损失曲面与更好泛化性能。
- 适合需要高精度重建的信号处理研究者。
我们提出一种新的集成框架，用于提升解决压缩感知问题的过参数化展开网络性能。将最先进的过参数化展开网络与延续技术结合，以暖启动该网络架构中的关键量；由此产生的连续网络称为C-DEC。此外，为训练和评估C-DEC，我们引入log-cosh损失函数，该函数兼具线性与二次行为。最后，我们在真实世界图像上数值评估了C-DEC的性能。结果表明，延续法与过参数化展开架构的结合，配合所选损失函数进行训练与评估，可带来更平滑的损失景观，并在所有数据集上持续提升重建精度与泛化能力。
原文摘要 · Abstract (English)
We present a new ensemble framework for boosting the performance of overparameterized unfolding networks solving the compressed sensing problem. We combine a state-of-the-art overparameterized unfolding network with a continuation technique, to warm-start a crucial quantity of the said network's architecture; we coin the resulting continued network C-DEC. Moreover, for training and evaluating C-DEC, we incorporate the log-cosh loss function, which enjoys both linear and quadratic behavior. Finally, we numerically assess C-DEC's performance on real-world images. Results showcase that the combination of continuation with the overparameterized unfolded architecture, trained and evaluated with the chosen loss function, yields smoother loss landscapes and improved reconstruction and generalization performance of C-DEC, consistently for all datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。