相关论文: Self-training with Noisy Student improves ImageNet…

Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to a semi-supervised learning problem by dividing training…

Despite the availability of large datasets for tasks like image classification and image-text alignment, labeled data for more complex recognition tasks, such as detection and segmentation, is less abundant. In particular, for instance…

Large datasets often have unreliable labels-such as those obtained from Amazon's Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhibit poor performance. We present a simple, effective…

Benchmark datasets in computer vision often contain off-topic images, near duplicates, and label errors, leading to inaccurate estimates of model performance. In this paper, we revisit the task of data cleaning and formalize it as either a…

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…

Recent studies on learning with noisy labels have shown remarkable performance by exploiting a small clean dataset. In particular, model agnostic meta-learning-based label correction methods further improve performance by correcting noisy…

While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power. Training…

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

We present a novel clustering objective that learns a neural network classifier from scratch, given only unlabelled data samples. The model discovers clusters that accurately match semantic classes, achieving state-of-the-art results in…

In many critical computer vision scenarios unlabeled data is plentiful, but labels are scarce and difficult to obtain. As a result, semi-supervised learning which leverages unlabeled data to boost the performance of supervised classifiers…

Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack…

Self-training is a classical approach in semi-supervised learning which is successfully applied to a variety of machine learning problems. Self-training algorithm generates pseudo-labels for the unlabeled examples and progressively refines…

With recently successful applications of deep learning in computer vision and general signal processing, deep learning has shown many unique advantages in medical signal processing. However, data labelling quality has become one of the most…

The convolutional neural networks (CNNs) trained on ILSVRC12 ImageNet were the backbone of various applications as a generic classifier, a feature extractor or a base model for transfer learning. This paper describes automated heuristics…

Robust learning from noisy demonstrations is a practical but highly challenging problem in imitation learning. In this paper, we first theoretically show that robust imitation learning can be achieved by optimizing a classification risk…

Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention.…

Deep neural networks have incredible capacity and expressibility, and can seemingly memorize any training set. This introduces a problem when training in the presence of noisy labels, as the noisy examples cannot be distinguished from clean…

We demonstrate, theoretically and empirically, that adversarial robustness can significantly benefit from semisupervised learning. Theoretically, we revisit the simple Gaussian model of Schmidt et al. that shows a sample complexity gap…

Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification tasks thanks to their regularization strategies. In this…

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we…