Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection

11/29/2021
by   Seong Min Kye, et al.
0

Recent studies on learning with noisy labels have shown remarkable performance by exploiting a small clean dataset. In particular, model agnostic meta-learning-based label correction methods further improve performance by correcting noisy labels on the fly. However, there is no safeguard on the label miscorrection, resulting in unavoidable performance degradation. Moreover, every training step requires at least three back-propagations, significantly slowing down the training speed. To mitigate these issues, we propose a robust and efficient method that learns a label transition matrix on the fly. Employing the transition matrix makes the classifier skeptical about all the corrected samples, which alleviates the miscorrection issue. We also introduce a two-head architecture to efficiently estimate the label transition matrix every iteration within a single back-propagation, so that the estimated matrix closely follows the shifting noise distribution induced by label correction. Extensive experiments demonstrate that our approach shows the best performance in training efficiency while having comparable or better accuracy than existing methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/02/2020

Extended T: Learning with Mixed Closed-set and Open-set Noisy Labels

The label noise transition matrix T, reflecting the probabilities that t...
research
04/02/2023

Adversary-Aware Partial label learning with Label distillation

To ensure that the data collected from human subjects is entrusted with ...
research
12/16/2022

Instance-specific Label Distribution Regularization for Learning with Label Noise

Modeling noise transition matrix is a kind of promising method for learn...
research
02/25/2023

Complementary to Multiple Labels: A Correlation-Aware Correction Approach

Complementary label learning (CLL) requires annotators to give irrelevan...
research
11/06/2019

Addressing Ambiguity of Emotion Labels Through Meta-learning

Emotion labels in emotion recognition corpora are highly noisy and ambig...
research
06/10/2020

Meta Transition Adaptation for Robust Deep Learning with Noisy Labels

To discover intrinsic inter-class transition probabilities underlying da...
research
03/26/2020

Matrix Smoothing: A Regularization for DNN with Transition Matrix under Noisy Labels

Training deep neural networks (DNNs) in the presence of noisy labels is ...

Please sign up or login with your details

Forgot password? Click here to reset