Related papers: Nuisances via Negativa: Adjusting for Spurious Cor…

Label noise is a critical factor that degrades the generalization performance of deep neural networks, thus leading to severe issues in real-world problems. Existing studies have employed strategies based on either loss or uncertainty to…

Researchers recently found out that sometimes language models achieve high accuracy on benchmark data set, but they can not generalize very well with even little changes to the original data set. This is sometimes due to data artifacts,…

Machine learning models tend to learn spurious features - features that strongly correlate with target labels but are not causal. Existing approaches to mitigate models' dependence on spurious features work in some cases, but fail in…

In real-world data, information is stored in extremely large feature vectors. These variables are typically correlated due to complex interactions involving many features simultaneously. Such correlations qualitatively correspond to…

Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…

We study the effect of imperfect training data labels on the performance of classification methods. In a general setting, where the probability that an observation in the training dataset is mislabelled may depend on both the feature vector…

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},…

Models that learn spurious correlations from training data often fail when deployed in new environments. While many methods aim to learn invariant representations to address this, they often underperform standard empirical risk minimization…

Rooting in the scarcity of most attributes, realistic pedestrian attribute datasets exhibit unduly skewed data distribution, from which two types of model failures are delivered: (1) label imbalance: model predictions lean greatly towards…

Supervised learning typically focuses on learning transferable representations from training examples annotated by humans. While rich annotations (like soft labels) carry more information than sparse annotations (like hard labels), they are…

Visual knowledge bases such as Visual Genome power numerous applications in computer vision, including visual question answering and captioning, but suffer from sparse, incomplete relationships. All scene graph models to date are limited to…

Spurious correlations that degrade model generalization or lead the model to be right for the wrong reasons are one of the main robustness concerns for real-world deployments. However, mitigating these correlations during pre-training for…

Distant supervision for relation extraction enables one to effectively acquire structured relations out of very large text corpora with less human efforts. Nevertheless, most of the prior-art models for such tasks assume that the given text…

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…

Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…

Deep learning models often achieve high performance by inadvertently learning spurious correlations between targets and non-essential features. For example, an image classifier may identify an object via its background that spuriously…

Semi-supervised (SS) semantic segmentation exploits both labeled and unlabeled images to overcome tedious and costly pixel-level annotation problems. Pseudolabel supervision is one of the core approaches of training networks with both…

We propose a novel sample selection method for image classification in the presence of noisy labels. Existing methods typically consider small-loss samples as correctly labeled. However, some correctly labeled samples are inherently…

We introduce a toolkit for uncovering spurious correlations between recording characteristics and target class in speech datasets. Spurious correlations may arise due to heterogeneous recording conditions, a common scenario for…

Instance features in images exhibit spurious correlations with background features, affecting the training process of deep neural classifiers. This leads to insufficient attention to instance features by the classifier, resulting in…