Related papers: Spurious Feature Diversification Improves Out-of-d…

Detecting Out-of-Distribution (OOD) samples in real world visual applications like classification or object detection has become a necessary precondition in today's deployment of Deep Learning systems. Many techniques have been proposed, of…

The training and test data for deep-neural-network-based classifiers are usually assumed to be sampled from the same distribution. When part of the test samples are drawn from a distribution that is sufficiently far away from that of the…

Existing out-of-distribution (OOD) detection literature clearly defines semantic shift as a sign of OOD but does not have a consensus over covariate shift. Samples experiencing covariate shift but not semantic shift are either excluded from…

The task of out-of-distribution (OOD) detection is crucial for deploying machine learning models in real-world settings. In this paper, we observe that the singular value distributions of the in-distribution (ID) and OOD features are quite…

Deep neural networks are susceptible to generating overconfident yet erroneous predictions when presented with data beyond known concepts. This challenge underscores the importance of detecting out-of-distribution (OOD) samples in the open…

Out-of-distribution (OOD) detection is essential for model trustworthiness which aims to sensitively identify semantic OOD samples and robustly generalize for covariate-shifted OOD samples. However, we discover that the superior OOD…

The credit spread is a key indicator in bond investments, offering valuable insights for fixed-income investors to devise effective trading strategies. This study proposes a novel credit spread forecasting model leveraging ensemble learning…

Machine learning methods must be trusted to make appropriate decisions in real-world environments, even when faced with out-of-distribution (OOD) samples. Many current approaches simply aim to detect OOD examples and alert the user when an…

Sparse Autoencoders (SAEs) have demonstrated significant success in interpreting Large Language Models (LLMs) by decomposing dense representations into sparse, semantic components. However, their potential for analyzing Vision Transformers…

Feature importance (FI) estimates are a popular form of explanation, and they are commonly created and evaluated by computing the change in model confidence caused by removing certain input features at test time. For example, in the…

Deep generative models (DGMs) seem a natural fit for detecting out-of-distribution (OOD) inputs, but such models have been shown to assign higher probabilities or densities to OOD images than images from the training distribution. In this…

Ensembles of deep neural networks demonstrate improved performance over single models. For enhancing the diversity of ensemble members while keeping their performance, particle-based inference methods offer a promising approach from a…

Sparse estimation methods capable of tolerating outliers have been broadly investigated in the last decade. We contribute to this research considering high-dimensional regression problems contaminated by multiple mean-shift outliers which…

Machine learning models are known to learn spurious correlations, i.e., features having strong relations with class labels but no causal relation. Relying on those correlations leads to poor performance in the data groups without these…

Out-of-Distribution(OOD) detection, a fundamental machine learning task aimed at identifying abnormal samples, traditionally requires model retraining for different inlier distributions. While recent research demonstrates the applicability…

Recent advances in out-of-distribution (OOD) detection on image data show that pre-trained neural network classifiers can separate in-distribution (ID) from OOD data well, leveraging the class-discriminative ability of the model itself.…

Out-of-distribution (OOD) detection helps models identify data outside the training categories, crucial for security applications. While feature-based post-hoc methods address this by evaluating data differences in the feature space without…

Detecting out-of-distribution (OOD) nodes in the graph-based machine-learning field is challenging, particularly when in-distribution (ID) node multi-category labels are unavailable. Thus, we focus on feature space rather than label space…

"Accuracy-on-the-line" is a widely observed phenomenon in machine learning, where a model's accuracy on in-distribution (ID) and out-of-distribution (OOD) data is positively correlated across different hyperparameters and data…

Out-of-distribution (OOD) detection is important for deploying machine learning models in the real world, where test data from shifted distributions can naturally arise. While a plethora of algorithmic approaches have recently emerged for…