Safeguarded Dynamic Label Regression for Generalized Noisy Supervision

by   Jiangchao Yao, et al.

Learning with noisy labels, which aims to reduce expensive labors on accurate annotations, has become imperative in the Big Data era. Previous noise transition based method has achieved promising results and presented a theoretical guarantee on performance in the case of class-conditional noise. However, this type of approaches critically depend on an accurate pre-estimation of the noise transition, which is usually impractical. Subsequent improvement adapts the pre-estimation along with the training progress via a Softmax layer. However, the parameters in the Softmax layer are highly tweaked for the fragile performance due to the ill-posed stochastic approximation. To address these issues, we propose a Latent Class-Conditional Noise model (LCCN) that naturally embeds the noise transition under a Bayesian framework. By projecting the noise transition into a Dirichlet-distributed space, the learning is constrained on a simplex based on the whole dataset, instead of some ad-hoc parametric space. We then deduce a dynamic label regression method for LCCN to iteratively infer the latent labels, to stochastically train the classifier and to model the noise. Our approach safeguards the bounded update of the noise transition, which avoids previous arbitrarily tuning via a batch of samples. We further generalize LCCN for open-set noisy labels and the semi-supervised setting. We perform extensive experiments with the controllable noise data sets, CIFAR-10 and CIFAR-100, and the agnostic noise data sets, Clothing1M and WebVision17. The experimental results have demonstrated that the proposed model outperforms several state-of-the-art methods.


page 1

page 2

page 6

page 8

page 9


Latent Class-Conditional Noise Model

Learning with noisy labels has become imperative in the Big Data era, wh...

Meta Transition Adaptation for Robust Deep Learning with Noisy Labels

To discover intrinsic inter-class transition probabilities underlying da...

Deep Learning from Noisy Image Labels with Quality Embedding

There is an emerging trend to leverage noisy image datasets in many visu...

Analysis of classifiers robust to noisy labels

We explore contemporary robust classification algorithms for overcoming ...

Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization

Many weakly supervised classification methods employ a noise transition ...

Two-Phase Learning for Overcoming Noisy Labels

To counter the challenge associated with noise labels, the learning stra...

Anti-perturbation of Online Social Networks by Graph Label Transition

Numerous popular online social networks (OSN) would classify users into ...

Please sign up or login with your details

Forgot password? Click here to reset