相关论文: Generative Reasoning Integrated Label Noise Robust…

Labelling of data for supervised learning can be costly and time-consuming and the risk of incorporating label noise in large data sets is imminent. When training a flexible discriminative model using a strictly proper loss, such noise will…

Noisy labels can negatively impact the performance of deep neural networks. One common solution is label refurbishment, which involves reconstructing noisy labels through predictions and distributions. However, these methods may introduce…

Labeled data is a fundamental component in training supervised deep learning models for computer vision tasks. However, the labeling process, especially for ordinal image classification where class boundaries are often ambiguous, is prone…

Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To harden models against…

Label noise may affect the generalization of classifiers, and the effective learning of main patterns from samples with noisy labels is an important challenge. Recent studies have shown that deep neural networks tend to prioritize the…

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…

Unified multimodal understanding and generation models recently have achieve significant improvement in image generation capability, yet a large gap remains in instruction following and detail preservation compared to systems that tightly…

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…

Generative recommendation provides a novel paradigm in which each item is represented by a discrete semantic ID (SID) learned from rich content. Most existing methods treat SIDs as predefined and train recommenders under static indexing. In…

Label noise has been broadly observed in real-world datasets. To mitigate the negative impact of overfitting to label noise for deep models, effective strategies (\textit{e.g.}, re-weighting, or loss rectification) have been broadly applied…

Composed Image Retrieval (CIR) is a challenging image retrieval paradigm that enables to retrieve target images based on multimodal queries consisting of reference images and modification texts. Although substantial progress has been made…

Although noisy-label learning is often approached with discriminative methods for simplicity and speed, generative modeling offers a principled alternative by capturing the joint mechanism that produces features, clean labels, and corrupted…

New Intent Discovery (NID) strives to identify known and reasonably deduce novel intent groups in the open-world scenario. But current methods face issues with inaccurate pseudo-labels and poor representation learning, creating a negative…

Label-noise or curated unlabeled data is used to compensate for the assumption of clean labeled data in training the conditional generative adversarial network; however, satisfying such an extended assumption is occasionally laborious or…

Fundus image classification is crucial in the computer aided diagnosis tasks, but label noise significantly impairs the performance of deep neural networks. To address this challenge, we propose a robust framework, Self-Supervised…

Feature noise and label noise are ubiquitous in practical scenarios, which pose great challenges for training a robust machine learning model. Most previous approaches usually deal with only a single problem of either feature noise or label…

Supervised learning, especially supervised deep learning, requires large amounts of labeled data. One approach to collect large amounts of labeled data is by using a crowdsourcing platform where numerous workers perform the annotation…

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,…

Despite the success of deep learning methods in medical image segmentation tasks, the human-level performance relies on massive training data with high-quality annotations, which are expensive and time-consuming to collect. The fact is that…

Temporal Graph Networks (TGNs) have shown remarkable performance in learning representation for continuous-time dynamic graphs. However, real-world dynamic graphs typically contain diverse and intricate noise. Noise can significantly…