相关论文: A New Robust Multivariate Mode Estimator for Eye-t…

Object tracking is an ubiquitous problem that appears in many applications such as remote sensing, audio processing, computer vision, human-machine interfaces, human-robot interaction, etc. Although thoroughly investigated in computer…

One of the early weaknesses identified in deep neural networks trained for image classification tasks was their inability to provide low confidence predictions on out-of-distribution (OOD) data that was significantly different from the…

We present a new methodology for detecting out-of-distribution (OOD) images by utilizing norms of the score estimates at multiple noise scales. A score is defined to be the gradient of the log density with respect to the input data. Our…

In an industrial context, the activity of sensors is recorded at a high frequency. A challenge is to automatically detect abnormal measurement behavior. Considering the sensor measures as functional data, the problem can be formulated as…

Measurement outliers are unavoidable when solving real-world robot state estimation problems. A large family of robust loss functions (RLFs) exists to mitigate the effects of outliers, including newly developed adaptive methods that do not…

Out-of-distribution (OOD) detection methods often exploit auxiliary outliers to train model identifying OOD samples, especially discovering challenging outliers from auxiliary outliers dataset to improve OOD detection. However, they may…

Modes and ridges of the probability density function behind observed data are useful geometric features. Mode-seeking clustering assigns cluster labels by associating data samples with the nearest modes, and estimation of density ridges…

Research on cluster analysis for categorical data continues to develop, with new clustering algorithms being proposed. However, in this context, the determination of the number of clusters is rarely addressed. In this paper, we propose a…

In recent, some robust contrastive multi-view clustering (MvC) methods have been proposed, which construct data pairs from neighborhoods to alleviate the false negative issue, i.e., some intra-cluster samples are wrongly treated as negative…

Metric $k$-center clustering is a fundamental unsupervised learning primitive. Although widely used, this primitive is heavily affected by noise in the data, so that a more sensible variant seeks for the best solution that disregards a…

We present an algorithmic and visual grouping of participants and eye-tracking metrics derived from recorded eye-tracking data. Our method utilizes two well-established visualization concepts. First, parallel coordinates are used to provide…

Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture…

In whole slide images (WSIs) analysis, attention-based multi-instance learning (MIL) models are susceptible to spurious correlations and degrade under domain shift. These methods may assign high attention weights to non-tumor regions, such…

Deep learning models often rely only on a small set of features even when there is a rich set of predictive signals in the training data. This makes models brittle and sensitive to distribution shifts. In this work, we first examine vision…

Multi-view clustering has shown to be an effective method for analyzing underlying patterns in multi-view data. The performance of clustering can be improved by learning the consistency and complementarity between multi-view features,…

We develop a novel approach to tackle the common but challenging problem of conformal inference for missing data in machine learning, focusing on Missing at Random (MAR) data. We propose a new procedure Conformal prediction for Missing data…

Continuous assessment of task difficulty and mental workload is essential in improving the usability and accessibility of interactive systems. Eye tracking data has often been investigated to achieve this ability, with reports on the…

Existing vision-language model (VLM)-based methods for out-of-distribution (OOD) detection typically rely on similarity scores between input images and in-distribution (ID) text prototypes. However, the modality gap between image and text…

This paper considers the problem of model selection under domain shift. Motivated by principles from distributionally robust optimisation and domain adaptation theory, it is proposed that the training-validation split should maximise the…

In the real world, a learning system could receive an input that is unlike anything it has seen during training. Unfortunately, out-of-distribution samples can lead to unpredictable behaviour. We need to know whether any given input belongs…