Related papers: Dynamic Metric Learning from Pairwise Comparisons

The linear ensemble based strategy, i.e., averaging ensemble, has been proposed to improve the performance in unsupervised domain adaptation tasks. However, a typical UDA task is usually challenged by dynamically changing factors, such as…

Coupled learning is a contrastive scheme for tuning the properties of individual elements within a network in order to achieve desired functionality of the system. It takes advantage of physics both to learn using local rules and to…

Online continual learning (OCL) methods adapt to changing environments without forgetting past knowledge. Similarly, online time series forecasting (OTSF) is a real-world problem where data evolve in time and success depends on both rapid…

Standard convolutions are prevalent in image processing and deep learning, but their fixed kernels limits adaptability. Several deformation strategies of the reference kernel grid have been proposed. Yet, they lack a unified theoretical…

Non-stationary online learning has drawn much attention in recent years. In particular, dynamic regret and adaptive regret are proposed as two principled performance measures for online convex optimization in non-stationary environments. To…

We analyze an online learning algorithm that adaptively combines outputs of two constituent algorithms (or the experts) running in parallel to model an unknown desired signal. This online learning algorithm is shown to achieve (and in some…

Contrastive learning methods, such as CLIP, leverage naturally paired data-for example, images and their corresponding text captions-to learn general representations that transfer efficiently to downstream tasks. While such approaches are…

We propose a novel adaptive, accelerated algorithm for the stochastic constrained convex optimization setting. Our method, which is inspired by the Mirror-Prox method, \emph{simultaneously} achieves the optimal rates for smooth/non-smooth…

Change detection, i.e. identification per pixel of changes for some classes of interest from a set of bi-temporal co-registered images, is a fundamental task in the field of remote sensing. It remains challenging due to unrelated forms of…

Online Continual Learning (OCL) for image classification represents a challenging subset of Continual Learning, focusing on classifying images from a stream without assuming data independence and identical distribution (i.i.d). The primary…

While metric learning is important for Person re-identification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires…

Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings. However, pairwise similarity computation in contrastive loss between image and…

Learning relational tabular data has gained significant attention recently, but most studies focus on single tables, overlooking the potential of cross-table learning. Cross-table learning, especially in scenarios where tables lack shared…

Clustering is a fundamental unsupervised learning approach. Many clustering algorithms -- such as $k$-means -- rely on the euclidean distance as a similarity measure, which is often not the most relevant metric for high dimensional data…

Effectively measuring the similarity between two human motions is necessary for several computer vision tasks such as gait analysis, person identi- fication and action retrieval. Nevertheless, we believe that traditional approaches such as…

We study the offline meta-reinforcement learning (OMRL) problem, a paradigm which enables reinforcement learning (RL) algorithms to quickly adapt to unseen tasks without any interactions with the environments, making RL truly practical in…

Adaptive spatial meshing has proven invaluable for the accurate, efficient computation of solutions of time dependent partial differential equations. In a DA context the use of adaptive spatial meshes addresses several factors that place…

Unsupervised deep metric learning (UDML) focuses on learning a semantic representation space using only unlabeled data. This challenging problem requires accurately estimating the similarity between data points, which is used to supervise a…

Clustering in high dimension spaces is a difficult task; the usual distance metrics may no longer be appropriate under the curse of dimensionality. Indeed, the choice of the metric is crucial, and it is highly dependent on the dataset…

Domain adaptation techniques address the problem of reducing the sensitivity of machine learning methods to the so-called domain shift, namely the difference between source (training) and target (test) data distributions. In particular,…