Related papers: Decoupling "when to update" from "how to update"
Incorrect labels in training data occur when human annotators make mistakes or when the data is generated via weak or distant supervision. It has been shown that complex noise-handling techniques - by modeling, cleaning or filtering the…
Deep Learning with noisy labels is a practically challenging problem in weakly supervised learning. The state-of-the-art approaches "Decoupling" and "Co-teaching+" claim that the "disagreement" strategy is crucial for alleviating the…
Deep neural networks have proven to be highly effective when large amounts of data with clean labels are available. However, their performance degrades when training data contains noisy labels, leading to poor generalization on the test…
Learning from noisy labels is a challenge that arises in many real-world applications where training data can contain incorrect or corrupted labels. When fine-tuning language models with noisy labels, models can easily overfit the label…
Large-scale datasets possessing clean label annotations are crucial for training Convolutional Neural Networks (CNNs). However, labeling large-scale data can be very costly and error-prone, and even high-quality datasets are likely to…
Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have an often-overlooked confounding effect on the assessment of model performance. Nevertheless, employing experts to…
Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with noisy labels, but such noise makes networks overfit seriously…
Labeling data correctly is an expensive and challenging task in machine learning, especially for on-line data streams. Deep learning models especially require a large number of clean labeled data that is very difficult to acquire in…
Deep neural networks (DNNs) can fit (or even over-fit) the training data very well. If a DNN model is trained using data with noisy labels and tested on data with clean labels, the model may perform poorly. This paper studies the problem of…
Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…
The need for labeled data is among the most common and well-known practical obstacles to deploying deep learning algorithms to solve real-world problems. The current generation of learning algorithms requires a large volume of data labeled…
Noisy labels are ubiquitous in real-world datasets, especially in the large-scale ones derived from crowdsourcing and web searching. It is challenging to train deep neural networks with noisy datasets since the networks are prone to…
Large datasets in NLP suffer from noisy labels, due to erroneous automatic and human annotation procedures. We study the problem of text classification with label noise, and aim to capture this noise through an auxiliary noise model over…
Label noise is ubiquitous in real-world scenarios, posing a practical challenge to supervised models due to its effect in hurting the generalization performance of deep neural networks. Existing methods primarily employ the sample selection…
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 such transition…
Label noise in the sense of incorrect labels is present in many real-world data sets and is known to severely limit the generalizability of deep learning models. In the field of remote sensing, however, automated treatment of label noise in…
Numerous researches have proved that deep neural networks (DNNs) can fit everything in the end even given data with noisy labels, and result in poor generalization performance. However, recent studies suggest that DNNs tend to gradually…
Visual sentiment analysis has received increasing attention in recent years. However, the dataset's quality is a concern because the sentiment labels are crowd-sourcing, subjective, and prone to mistakes, and poses a severe threat to the…
Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time. To overcome this problem, we present a simple and effective method self-ensemble label filtering (SELF) to…
Smart sensing provides an easier and convenient data-driven mechanism for monitoring and control in the built environment. Data generated in the built environment are privacy sensitive and limited. Federated learning is an emerging paradigm…