Related papers: Robust Learning by Self-Transition for Handling No…

Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model. To overcome this issue, we propose a new approach for learning from noisy labels (LNL) via…

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…

Optimizing neural networks with noisy labels is a challenging task, especially if the label set contains real-world noise. Networks tend to generalize to reasonable patterns in the early training stages and overfit to specific details of…

Learning with Noisy Labels (LNL) has attracted significant attention from the research community. Many recent LNL methods rely on the assumption that clean samples tend to have "small loss". However, this assumption always fails to…

We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and…

Deep neural networks have achieved remarkable success in a wide variety of natural image and medical image computing tasks. However, these achievements indispensably rely on accurately annotated training data. If encountering some…

Noisy label learning aims to learn robust networks under the supervision of noisy labels, which plays a critical role in deep learning. Existing work either conducts sample selection or label correction to deal with noisy labels during the…

Source-free domain adaptation aims to adapt a source-trained model to an unlabeled target domain without access to the source data. It has attracted growing attention in recent years, where existing approaches focus on self-training that…

Designing robust algorithms capable of training accurate neural networks on uncurated datasets from the web has been the subject of much research as it reduces the need for time consuming human labor. The focus of many previous research…

We propose a framework using contrastive learning as a pre-training task to perform image classification in the presence of noisy labels. Recent strategies such as pseudo-labeling, sample selection with Gaussian Mixture models, weighted…

Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance.…

To collect large scale annotated data, it is inevitable to introduce label noise, i.e., incorrect class labels. To be robust against label noise, many successful methods rely on the noisy classifiers (i.e., models trained on the noisy…

Due to the existence of label noise in web images and the high memorization capacity of deep neural networks, training deep fine-grained (FG) models directly through web images tends to have an inferior recognition ability. In the…

Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions. Inspired by the success of generative diffusion models, we propose a novel approach of…

Mislabeled samples are ubiquitous in real-world datasets as rule-based or expert labeling is usually based on incorrect assumptions or subject to biased opinions. Neural networks can "memorize" these mislabeled samples and, as a result,…

Multi-label image classification has generated significant interest in recent years and the performance of such systems often suffers from the not so infrequent occurrence of incorrect or missing labels in the training data. In this paper,…

Robust loss minimization is an important strategy for handling robust learning issue on noisy labels. Current robust loss functions, however, inevitably involve hyperparameter(s) to be tuned, manually or heuristically through cross…

Current state-of-the-art deep learning systems for visual object recognition and detection use purely supervised training with regularization such as dropout to avoid overfitting. The performance depends critically on the amount of labeled…

Label noise is ubiquitous in various machine learning scenarios such as self-labeling with model predictions and erroneous data annotation. Many existing approaches are based on heuristics such as sample losses, which might not be flexible…

Learning with noisy labels (LNL) is essential for training deep neural networks with imperfect data. Meta-learning approaches have achieved success by using a clean unbiased labeled set to train a robust model. However, this approach…