Joint Optimization Framework for Learning with Noisy Labels
نویسندگان
چکیده
Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are termed as noisy labels. Training on such noisy labeled datasets causes performance degradation because DNNs easily overfit to noisy labels. To overcome this problem, we propose a joint optimization framework of learning DNN parameters and estimating true labels. Our framework can correct labels during training by alternating update of network parameters and labels. We conduct experiments on the noisy CIFAR-10 datasets and the Clothing1M dataset. The results indicate that our approach significantly outperforms other state-of-the-art methods.
منابع مشابه
A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels
The recent success of deep neural networks is powered in part by large-scale well-labeled training data. However, it is a daunting task to laboriously annotate an ImageNet-like dateset. On the contrary, it is fairly convenient, fast, and cheap to collect training images from the Web along with their noisy labels. This signifies the need of alternative approaches to training deep neural networks...
متن کاملUnsupervised Learning from Noisy Networks with Applications to Hi-C Data
Complex networks play an important role in a plethora of disciplines in natural sciences. Cleaning up noisy observed networks, poses an important challenge in network analysis Existing methods utilize labeled data to alleviate the noise effect in the network. However, labeled data is usually expensive to collect while unlabeled data can be gathered cheaply. In this paper, we propose an optimiza...
متن کاملJoint Syntactic and Semantic Analysis with a Multitask Deep Learning Framework for Spoken Language Understanding
Spoken Language Understanding (SLU) models have to deal with Automatic Speech Recognition outputs which are prone to contain errors. Most of SLU models overcome this issue by directly predicting semantic labels from words without any deep linguistic analysis. This is acceptable when enough training data is available to train SLU models in a supervised way. However for open-domain SLU, such anno...
متن کاملRegularized maximum correntropy machine
In this paper we investigate the usage of regularized correntropy framework for learning of classifiers from noisy labels. The class label predictors learned by minimizing transitional loss functions are sensitive to the noisy and outlying labels of training samples, because the transitional loss functions are equally applied to all the samples. To solve this problem, we propose to learn the cl...
متن کاملDeep Learning from Noisy Image Labels with Quality Embedding
There is an emerging trend to leverage noisy image datasets in many visual recognition tasks. However, the label noise among the datasets severely degenerates the performance of deep learning approaches. Recently, one mainstream is to introduce the latent label to handle label noise, which has shown promising improvement in the network designs. Nevertheless, the mismatch between latent labels a...
متن کامل