Related papers: Noisy Student Training using Body Language Dataset…

Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect. There…

Voice activity detection is an essential pre-processing component for speech-related tasks such as automatic speech recognition (ASR). Traditional supervised VAD systems obtain frame-level labels from an ASR pipeline by using, e.g., a…

The availability of large labeled datasets has allowed Convolutional Network models to achieve impressive recognition results. However, in many settings manual annotation of the data is impractical; instead our data has noisy labels, i.e.…

We present Noisy Student Training, a semi-supervised learning approach that works well even when labeled data is abundant. Noisy Student Training achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of-the-art…

ConvNets achieve good results when training from clean data, but learning from noisy labels significantly degrades performances and remains challenging. Unlike previous works constrained by many conditions, making them infeasible to real…

When there is a mismatch between the training and test domains, current speech recognition systems show significant performance degradation. Self-training methods, such as noisy student teacher training, can help address this and enable the…

Although deep face recognition benefits significantly from large-scale training data, a current bottleneck is the labelling cost. A feasible solution to this problem is semi-supervised learning, exploiting a small portion of labelled data…

A novel procedure is presented in this paper, for training a deep convolutional and recurrent neural network, taking into account both the available training data set and some information extracted from similar networks trained with other…

Deep learning has shown remarkable progress in a wide range of problems. However, efficient training of such models requires large-scale datasets, and getting annotations for such datasets can be challenging and costly. In this work, we…

Recent progress in singing voice separation has primarily focused on supervised deep learning methods. However, the scarcity of ground-truth data with clean musical sources has been a problem for long. Given a limited set of labeled data,…

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…

Datasets with significant proportions of noisy (incorrect) class labels present challenges for training accurate Deep Neural Networks (DNNs). We propose a new perspective for understanding DNN generalization for such datasets, by…

Training Deep neural networks (DNNs) on noisy labeled datasets is a challenging problem, because learning on mislabeled examples deteriorates the performance of the network. As the ground truth availability is limited with real-world noisy…

We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest…

Facial expressions and actions differ among different individuals at varying degrees of intensity given responses to external stimuli, particularly among those that are neurodivergent. Such behaviors affect people in terms of overall…

Benefit from large-scale training datasets, deep Convolutional Neural Networks(CNNs) have achieved impressive results in face recognition(FR). However, tremendous scale of datasets inevitably lead to noisy data, which obviously reduce the…

Machine learning systems are being used to automate many types of laborious labeling tasks. Facial actioncoding is an example of such a labeling task that requires copious amounts of time and a beyond average level of human domain…

Constructing fine-grained image datasets typically requires domain-specific expert knowledge, which is not always available for crowd-sourcing platform annotators. Accordingly, learning directly from web images becomes an alternative method…

In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount of training data. However, in a low-resource scenario, it is…

Deep learning methods have shown outstanding classification accuracy in medical imaging problems, which is largely attributed to the availability of large-scale datasets manually annotated with clean labels. However, given the high cost of…