Related papers: The Cumulative Distribution Transform and Linear P…

The problem of detecting changes with multiple sensors has received significant attention in the literature. In many practical applications such as critical infrastructure monitoring and modeling of disease spread, a useful change…

The linear classifier is widely used in various image classification tasks. It works by optimizing the distance between a sample and its corresponding class center. However, in real-world data, one class can contain several local clusters,…

A new model that describes adsorption and clustering of particles on a surface is introduced. A {\it clustering} transition is found which separates between a phase of weakly correlated particle distributions and a phase of strongly…

Continual Test-Time Adaptation (CTTA) is an emerging and challenging task where a model trained in a source domain must adapt to continuously changing conditions during testing, without access to the original source data. CTTA is prone to…

We present a novel class of convolutional neural networks (CNNs) for set functions, i.e., data indexed with the powerset of a finite set. The convolutions are derived as linear, shift-equivariant functions for various notions of shifts on…

This paper presents Camera-LiDAR Fusion Transformer (CLFT) models for traffic object segmentation, which leverage the fusion of camera and LiDAR data using vision transformers. Building on the methodology of visual transformers that exploit…

The direct Gaussian copula model with discrete marginal distributions is an appealing data-analytic tool but poses difficult computational challenges due to its intractable likelihood. A number of approximations/surrogates for the…

How could the Fourier and other transforms be naturally discovered if one didn't know how to postulate them? In the case of the Discrete Fourier Transform (DFT), we show how it arises naturally out of analysis of circulant matrices. In…

Waste recycling is an important way of saving energy and materials in the production process. In general cases recyclable objects are mixed with unrecyclable objects, which raises a need for identification and classification. This paper…

The increased success of Deep Learning (DL) has recently sparked large-scale deployment of DL models in many diverse industry segments. Yet, a crucial weakness of supervised model is the inherent difficulty in handling out-of-distribution…

This work simultaneously considers the discriminability and transferability properties of deep representations in the typical supervised learning task, i.e., image classification. By a comprehensive temporal analysis, we observe a trade-off…

Remote sensing change detection is crucial for understanding the dynamics of our planet's surface, facilitating the monitoring of environmental changes, evaluating human impact, predicting future trends, and supporting decision-making. In…

With the proliferation of social media platforms and e-commerce sites, several cross-domain collaborative filtering strategies have been recently introduced to transfer the knowledge of user preferences across domains. The main challenge of…

In many real-world scenarios, data to train machine learning models become available over time. However, neural network models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon…

While mixture density networks (MDNs) have been extensively used for regression tasks, they have not been used much for classification tasks. One reason for this is that the usability of MDNs for classification is not clear and…

This paper offers a mathematical invention that shows how to convert integrated quantiles, which often appear in risk measures, into integrated cumulative distribution functions, which are technically more tractable from various…

Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity. While such models offer a number of compelling benefits, it has been…

Transformer-based detection and segmentation methods use a list of learned detection queries to retrieve information from the transformer network and learn to predict the location and category of one specific object from each query. We…

Cross-lingual text classification(CLTC) is the task of classifying documents written in different languages into the same taxonomy of categories. This paper presents a novel approach to CLTC that builds on model distillation, which adapts…

A continual learning solution is proposed to address the out-of-distribution generalization problem for pedestrian detection. While recent pedestrian detection models have achieved impressive performance on various datasets, they remain…