Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning
For learning with noisy labels, the transition matrix, which explicitly models the relation between noisy label distribution and clean label distribution, has been utilized to achieve the statistical consistency of either the classifier or the risk. Previous researches have focused more on how to estimate this transition matrix well, rather than how to utilize it. We propose good utilization of the transition matrix is crucial and suggest a new utilization method based on resampling, coined RENT. Specifically, we first demonstrate current utilizations can have potential limitations for implementation. As an extension to Reweighting, we suggest the Dirichlet distribution-based per-sample Weight Sampling (DWS) framework, and compare reweighting and resampling under DWS framework. With the analyses from DWS, we propose RENT, a REsampling method with Noise Transition matrix. Empirically, RENT consistently outperforms existing transition matrix utilization methods, which includes reweighting, on various benchmark datasets. Our code is available at \url{https://github.com/BaeHeeSun/RENT}.
Code (1)
Tasks
Learning with noisy labelsSimilar Papers 제목 키워드 기반
Robust Recommendation from Noisy Implicit Feedback: A GMM-Weighted Bayes-label Transition Matrix Framework
Learning from implicit feedback in recommender systems is fundamentally challenged by pervasive label noise. While conventional denoising approaches often discard noisy instances to ensure robustness, this strategy inevi…
Meta Transition Adaptation for Robust Deep Learning with Noisy Labels
To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted labels. Prior methods attempt to achieve s…
Deep LearningLearning with noisy labelsAlleviating Noisy-label Effects in Image Classification via Probability Transition Matrix
Deep-learning-based image classification frameworks often suffer from the noisy label problem caused by the inter-observer variation. Recent studies employed learning-to-learn paradigms (e.g., Co-teaching and JoCoR) to f…
image-classificationImage ClassificationDetect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels
Falsely annotated samples, also known as noisy labels, can significantly harm the performance of deep learning models. Two main approaches for learning with noisy labels are global noise estimation and data filtering. Gl…
Learning with noisy labelsNoise EstimationA Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics
Probabilistic approaches for handling count-valued time sequences have attracted amounts of research attentions because their ability to infer explainable latent structures and to estimate uncertainties, and thus are esp…
Data AugmentationTime Series