REVIEW 7 cited by
SELF: Learning to Filter Noisy Labels with Self-Ensembling
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time. To overcome this problem, we present a simple and effective method self-ensemble label filtering (SELF) to progressively filter out the wrong labels during training. Our method improves the task performance by gradually allowing supervision only from the potentially non-noisy (clean) labels and stops learning on the filtered noisy labels. For the filtering, we form running averages of predictions over the entire training dataset using the network output at different training epochs. We show that these ensemble estimates yield more accurate identification of inconsistent predictions throughout training than the single estimates of the network at the most recent training epoch. While filtered samples are removed entirely from the supervised training loss, we dynamically leverage them via semi-supervised learning in the unsupervised loss. We demonstrate the positive effect of such an approach on various image classification tasks under both symmetric and asymmetric label noise and at different noise ratios. It substantially outperforms all previous works on noise-aware learning across different datasets and can be applied to a broad set of network architectures.
Forward citations
Cited by 7 Pith papers
-
Tackling the Noisy Elephant in the Room: Label Noise-robust Out-of-Distribution Detection via Loss Correction and Low-rank Decomposition
NOODLE corrects noisy labels with a transition matrix and cleans features via low-rank sparse decomposition, improving OOD detection under label noise.
-
Commuting Distance Regularization for Timescale-Dependent Label Inconsistency in EEG Emotion Recognition
Graph-commute-distance regularizers LVL and LGCL improve aggregate rank of EEG emotion recognition under label inconsistency across three backbones on DREAMER and DEAP.
-
Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement
SiDyP improves classifiers trained on LLM-generated noisy labels by retrieving likely true labels from embedding-space neighbors and iteratively refining them with a simplex diffusion model, reporting average gains of...
-
MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality images
Pairing high-difficulty with low-difficulty images, ranked by loss and uncertainty, makes minibatch training more effective and improves accuracy on four computer vision tasks.
-
Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
For binary classification with noisy labels, the paper derives the Bayes-optimal function for combining a model's current predictions with the given labels during retraining, and shows a fitted version improves linear...
-
Unleashing the Power of Large Language Model for Denoising Recommendation
LLaRD uses LLM-generated preference and relation knowledge plus an information-bottleneck objective to denoise implicit feedback and improve recommendation accuracy on Steam, Yelp, and Amazon-Book.
-
Why Can Accurate Models Be Learned from Inaccurate Annotations?
Principal subspaces of classifier weights are largely preserved under moderate label inaccuracy, which explains why models still learn from noisy labels.
Discussion (0). Continue with ORCID to comment.