Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Noise2Noise Revisited: Training Pair Distributions Dominate Loss Choice in Self-Supervised Denoising
Dingyan Shang, Zhenyu Xu, Youting Wang +2
Noise2Noise (N2N) trains denoisers on pairs of independently corrupted observations, eliminating clean references. We stress-test two natural conjectures about why the L1 loss outp…
cs.LG2026
AdaStop: Cost-Aware Early Stopping for DNN Test Selection
Bonan Shen, Wei-Jung Huang, Xin Liu +2
Existing methods for testing deep neural networks (DNNs) primarily prioritize test inputs likely to reveal model faults under a fixed labeling budget. In practice, choosing that bu…