A Principled Self-Referenced Early Stopping Approach for Deep Image Prior 事件

A Principled Self-Referenced Early Stopping Approach for Deep Image Prior arXiv:2605.25299v1 Announce Type: new Abstract: Recently, Deep Image Prior (DIP) has demonstrated strong capabilities for solving inverse imaging problems (IIPs) by optimizing a randomly initialized convolutional neural network in a training-data-free regime. However, DIP suffers from overfitting to noisy measurements due to network over-parameterization, making early stopping (ES) essential. The most successful ES method