Related papers: Noise-Tolerant Hybrid Prototypical Learning with N…

Modern deep learning systems are data-hungry. Learning with web data is one of the feasible solutions, but will introduce label noise inevitably, which can hinder the performance of deep neural networks. Sample selection is an effective way…

Learning with Noisy Labels (LNL) has become an appealing topic, as imperfectly annotated data are relatively cheaper to obtain. Recent state-of-the-art approaches employ specific selection mechanisms to separate clean and noisy samples and…

Studies show that refining real-world categories into semantic subcategories contributes to better image modeling and classification. Previous image sub-categorization work relying on labeled images and WordNet's hierarchy is not only…

Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise,…

Learning from noisy labels (LNL) is crucial in deep learning, in which one of the approaches is to identify clean-label samples from poorly-annotated datasets. Such an identification is challenging because the conventional LNL problem,…

With the development of deep learning, medical image classification has been significantly improved. However, deep learning requires massive data with labels. While labeling the samples by human experts is expensive and time-consuming,…

Learning with Noisy labels (LNL) poses a significant challenge for the Machine Learning community. Some of the most widely used approaches that select as clean samples for which the model itself (the in-training model) has high confidence,…

Image noise modeling is a long-standing problem with many applications in computer vision. Early attempts that propose simple models, such as signal-independent additive white Gaussian noise or the heteroscedastic Gaussian noise model…

Large-scale datasets have driven the rapid development of deep neural networks for visual recognition. However, annotating a massive dataset is expensive and time-consuming. Web images and their labels are, in comparison, much easier to…

In recent years, deep neural networks (DNNs) have gained remarkable achievement in computer vision tasks, and the success of DNNs often depends greatly on the richness of data. However, the acquisition process of data and high-quality…

Collecting large-scale data with clean labels for supervised training of neural networks is practically challenging. Although noisy labels are usually cheap to acquire, existing methods suffer a lot from label noise. This paper targets at…

The label noise transition matrix, denoting the transition probabilities from clean labels to noisy labels, is crucial for designing statistically robust solutions. Existing estimators for noise transition matrices, e.g., using either…

Noisy training set usually leads to the degradation of generalization and robustness of neural networks. In this paper, we propose using a theoretically guaranteed noisy label detection framework to detect and remove noisy data for Learning…

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…

Current vision systems are trained on huge datasets, and these datasets come with costs: curation is expensive, they inherit human biases, and there are concerns over privacy and usage rights. To counter these costs, interest has surged in…

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 \mbox{performance of deep} learning approaches. Recently, one mainstream is…

Learning with noisy labels aims to ensure model generalization given a label-corrupted training set. The sample selection strategy achieves promising performance by selecting a label-reliable subset for model training. In this paper, we…

Manually annotating datasets for training deep models is very labor-intensive and time-consuming. To overcome such inferiority, directly leveraging web images to conduct training data becomes a natural choice. Nevertheless, the presence of…

State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their intersection-over-union (IoU) with corresponding groundtruth…

Most existing image denoising approaches assumed the noise to be homogeneous white Gaussian distributed with known intensity. However, in real noisy images, the noise models are usually unknown beforehand and can be much more complex. This…