Related papers: AEON: Adaptive Estimation of Instance-Dependent In…

Robust out-of-distribution (OOD) detection is an indispensable component of modern artificial intelligence (AI) systems, especially in safety-critical applications where models must identify inputs from unfamiliar classes not seen during…

Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presence of instance-dependent noise (IDN), a realistic form of…

Out-of-Distribution (OOD) detection is essential in real-world applications, which has attracted increasing attention in recent years. However, most existing OOD detection methods require many labeled In-Distribution (ID) data, causing a…

Noisy labels are unavoidable yet troublesome in the ecosystem of deep learning because models can easily overfit them. There are many types of label noise, such as symmetric, asymmetric and instance-dependent noise (IDN), with IDN being the…

The ability to detect unfamiliar or unexpected images is essential for safe deployment of computer vision systems. In the context of classification, the task of detecting images outside of a model's training domain is known as…

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…

Noisy training labels can hurt model performance. Most approaches that aim to address label noise assume label noise is independent from the input features. In practice, however, label noise is often feature or \textit{instance-dependent},…

Robustness in AI systems refers to their ability to maintain reliable and accurate performance under various conditions, including out-of-distribution (OOD) samples, adversarial attacks, and environmental changes. This is crucial in…

Label noise in multiclass classification is a major obstacle to the deployment of learning systems. However, unlike the widely used class-conditional noise (CCN) assumption that the noisy label is independent of the input feature given the…

The discrepancy between in-distribution (ID) and out-of-distribution (OOD) samples can lead to \textit{distributional vulnerability} in deep neural networks, which can subsequently lead to high-confidence predictions for OOD samples. This…

Label noise widely exists in large-scale datasets and significantly degenerates the performances of deep learning algorithms. Due to the non-identifiability of the instance-dependent noise transition matrix, most existing algorithms address…

In supervised machine learning, the assumption that training data is labelled correctly is not always satisfied. In this paper, we investigate an instance of labelling error for classification tasks in which the dataset is corrupted with…

Existing research on learning with noisy labels predominantly focuses on synthetic label noise. Although synthetic noise possesses well-defined structural properties, it often fails to accurately replicate real-world noise patterns. In…

Out-of-distribution (OOD) detection lies at the heart of robust artificial intelligence (AI), aiming to identify samples from novel distributions beyond the training set. Recent approaches have exploited feature representations as…

Noisy labels severely hinder the accuracy and generalization of machine learning models, especially when ambiguous instance features make reliable annotation difficult. Existing approaches, including transition-matrix-based label…

Noise transition matrix (NTM) estimation is a promising approach for learning with label noise. It can infer clean posterior probabilities, known as Label Distribution (LD), based on noisy ones and reduce the impact of noisy labels.…

The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated…

Learning with noisy labels (LNL) is typically benchmarked by closed-set classification accuracy, yet deployment often requires classifiers to reject out-of-distribution (OOD) inputs. We present a learner-agnostic ACC-OOD benchmark that…

Learning from noisy-labeled data is crucial for real-world applications. Traditional Noisy-Label Learning (NLL) methods categorize training data into clean and noisy sets based on the loss distribution of training samples. However, they…

In learning with noisy labels, for every instance, its label can randomly walk to other classes following a transition distribution which is named a noise model. Well-studied noise models are all instance-independent, namely, the transition…