Related papers: Private Semi-supervised Knowledge Transfer for Dee…
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…
As tons of photos are being uploaded to public websites (e.g., Flickr, Bing, and Google) every day, learning from web data has become an increasingly popular research direction because of freely available web resources, which is also…
Class imbalance and noisy labels are the norm rather than the exception in many large-scale classification datasets. Nevertheless, most works in machine learning typically assume balanced and clean data. There have been some recent attempts…
Deep neural networks have achieved remarkable performance across various tasks when supplied with large-scale labeled data. However, the collection of labeled data can be time-consuming and labor-intensive. Semi-supervised learning (SSL),…
While deep models have proved successful in learning rich knowledge from massive well-annotated data, they may pose a privacy leakage risk in practical deployment. It is necessary to find an effective trade-off between high utility and…
Federated learning is a paradigm that enables local devices to jointly train a server model while keeping the data decentralized and private. In federated learning, since local data are collected by clients, it is hardly guaranteed that the…
Class labels are often imperfectly observed, due to mistakes and to genuine ambiguity among classes. We propose a new semi-supervised deep generative model that explicitly models noisy labels, called the Mislabeled VAE (M-VAE). The M-VAE…
Labeling real-world datasets is time consuming but indispensable for supervised machine learning models. A common solution is to distribute the labeling task across a large number of non-expert workers via crowd-sourcing. Due to the varying…
In this paper, we investigate the problem of learning with noisy labels in real-world annotation scenarios, where noise can be categorized into two types: factual noise and ambiguity noise. To better distinguish these noise types and…
We introduce a novel method for training machine learning models in the presence of noisy labels, which are prevalent in domains such as medical diagnosis and autonomous driving and have the potential to degrade a model's generalization…
Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade the generalization of models and result in memorizing samples,…
While computer vision and machine learning have made great progress, their robustness is still challenged by two key issues: data distribution shift and label noise. When domain generalization (DG) encounters noise, noisy labels further…
Distantly-Supervised Named Entity Recognition (DS-NER) is widely used in real-world scenarios. It can effectively alleviate the burden of annotation by matching entities in existing knowledge bases with snippets in the text but suffer from…
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…
Weakly-supervised text classification trains a classifier using the label name of each target class as the only supervision, which largely reduces human annotation efforts. Most existing methods first use the label names as static…
In learning tasks with label noise, improving model robustness against overfitting is a pivotal challenge because the model eventually memorizes labels, including the noisy ones. Identifying the samples with noisy labels and preventing the…
Noisy labels, resulting from mistakes in manual labeling or webly data collecting for supervised learning, can cause neural networks to overfit the misleading information and degrade the generalization performance. Self-supervised learning…
Deep learning models for plant species identification rely on large annotated datasets. The PlantNet system enables global data collection by allowing users to upload and annotate plant observations, leading to noisy labels due to diverse…
Point cloud segmentation is a fundamental task in 3D. Despite recent progress on point cloud segmentation with the power of deep networks, current deep learning methods based on the clean label assumptions may fail with noisy labels. Yet,…
Samples with ground truth labels may not always be available in numerous domains. While learning from crowdsourcing labels has been explored, existing models can still fail in the presence of sparse, unreliable, or diverging annotations.…