A discriminator trained to distinguish clean from corrupt image-label pairs can be used during sampling to correct the score of a noisy-label conditional diffusion model, improving class-wise fidelity without retraining.
Robust Training with Ensemble Consensus
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Since deep neural networks are over-parameterized, they can memorize noisy examples. We address such a memorization issue in the presence of label noise. From the fact that deep neural networks cannot generalize to neighborhoods of memorized features, we hypothesize that noisy examples do not consistently incur small losses on the network under a certain perturbation. Based on this, we propose a novel training method called Learning with Ensemble Consensus (LEC) that prevents overfitting to noisy examples by removing them based on the consensus of an ensemble of perturbed networks. One of the proposed LECs, LTEC outperforms the current state-of-the-art methods on noisy MNIST, CIFAR-10, and CIFAR-100 in an efficient manner.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Guiding Noisy Label Conditional Diffusion Models with Score-based Discriminator Correction
A discriminator trained to distinguish clean from corrupt image-label pairs can be used during sampling to correct the score of a noisy-label conditional diffusion model, improving class-wise fidelity without retraining.