arXiv research

A new metric-based principal curve method learns 1D manifolds from spatial data.

A new method for automatically learning metric scaling in metric-based meta-learning.

Paper proposes adaptive margin loss to improve few-shot learning.

This research tackles few-shot video action recognition, improving accuracy with a two-stream setup.

Few-shot learning aims to learn classifiers for new classes with only a few training examples per class. Most existing few-shot learning approaches belong to either metric-based meta-learning or optimization-based meta-learning category, both of which have achieved successes in the simplified "$k$-shot $N$-way" image c…

This paper introduces depth functions for ranking data, improving statistical summaries.

Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic feature spaces have different structures by definition. For certain concepts, vis…

A novel approach for unsupervised domain adaptation for neural networks is proposed. It relies on metric-based regularization of the learning process. The metric-based regularization aims at domain-invariant latent feature representations by means of maximizing the similarity between domain-specific activation distribu…

The key issue of few-shot learning is learning to generalize. This paper proposes a large margin principle to improve the generalization capacity of metric based methods for few-shot learning. To realize it, we develop a unified framework to learn a more discriminative metric space by augmenting the classification loss…

Paper classifies Randers metrics based on Ricci curvature properties.

Metric-based few-shot learning methods try to overcome the difficulty due to the lack of training examples by learning embedding to make comparison easy. We propose a novel algorithm to generate class representatives for few-shot classification tasks. As a probabilistic model for learned features of inputs, we consider…

Lagrangian data assimilation is a complex problem in oceanic and atmospheric modeling. Tracking drifters in large-scale geophysical flows can involve uncertainty in drifter location, complex inertial effects, and other factors which make comparing them to simulated Lagrangian trajectories from numerical models extremel…

Study of classification in asymmetric quasi-metric spaces.

In this paper, we address the problem of hidden common variables discovery from multimodal data sets of nonlinear high-dimensional observations. We present a metric based on local applications of canonical correlation analysis (CCA) and incorporate it in a kernel-based manifold learning technique.We show that this metr…

3D metrics get scalar curvature bounds via IMCF.

The Schwarz--Pick lemma is a fundamental result in complex analysis. It is well-known that Yau generalized it to the higher dimensional manifolds by applying his maximum principle for complete Riemannian manifolds. Jeffres obtained Schwarz lemma for volume forms of conical Kähler metrics, based on a barrier function an…

New method uses contrastively trained GNNs for more reliable graph model evaluation.

COMPASS improves uncertainty quantification for medical segmentation metrics.

New ensemble models classify mouse movement trajectories to assess survey question difficulty.

Study evaluates thresholds for removing noise from DNN weights using random matrix theory.

New method quantifies classifier uncertainty, revealing large variability in performance metrics.

Incremental class learning, a scenario in continual learning context where classes and their training data are sequentially and disjointedly observed, challenges a problem widely known as catastrophic forgetting. In this work, we propose a novel incremental class learning method that can significantly reduce memory ove…

New metrics assess class overlap and imbalance in datasets.

New metric defines surface shapes, minimizing area and angle distortions.

Study categorizes time series anomaly detection metrics based on evaluation challenges.

Solves Lempert's question on Nakano semi-positivity preservation.

A new stock selection strategy uses combined machine learning with dynamic weighting methods.

Estimates bisimulation metrics from sample streams, not full transition models.

Defines a new Randers metric based on an existing one.

The Wasserstein distance is a powerful metric based on the theory of optimal transport. It gives a natural measure of the distance between two distributions with a wide range of applications. In contrast to a number of the common divergences on distributions such as Kullback-Leibler or Jensen-Shannon, it is (weakly) co…

FSN model improves few-shot learning by generalizing to new tasks.

In order to design haptic icons or build a haptic vocabulary, we require a set of easily distinguishable haptic signals to avoid perceptual ambiguity, which in turn requires a way to accurately estimate the perceptual (dis)similarity of such signals. In this work, we present a novel method to learn such a perceptual me…

Study analyzes neural network models to understand generalization performance.

Paper proposes Coalitional BAE to improve explainability of unsupervised deep learning models.

ProGen models protein sequences for synthetic biology.

Assessing the performance of a learned model is a crucial part of machine learning. However, in some domains only positive and unlabeled examples are available, which prohibits the use of most standard evaluation metrics. We propose an approach to estimate any metric based on contingency tables, including ROC and PR cu…

Maximizing product use is a central goal of many businesses, which makes retention and monetization two central analytics metrics in games. Player retention may refer to various duration variables quantifying product use: total playtime or session playtime are popular research targets, and active playtime is well-suite…

Random layer-wise pruning profiles are as effective as metric-based ones for various datasets.

In machine learning, novelty detection is the task of identifying novel unseen data. During training, only samples from the normal class are available. Test samples are classified as normal or abnormal by assignment of a novelty score. Here we propose novelty detection methods based on training variational autoencoders…

Image captioning has demonstrated models that are capable of generating plausible text given input images or videos. Further, recent work in image generation has shown significant improvements in image quality when text is used as a prior. Our work ties these concepts together by creating an architecture that can enabl…

We study conformal metrics on $R^3$, i.e., metrics of the form $g_u=e^{2u}|dx|^2$, which have constant $Q$-curvature and finite volume. This is equivalent to studying the non-local equation $(-Δ)^\frac32 u = 2 e^{3u}$ in $R^3$ $V:=\int_{\mathbb{R}^3}e^{3u}dx<\infty,$ where $V$ is the volume of $g_u$. Adapting a te…

Improves few-shot learning using multi-task representation learning theory.

Optimization-based pruning eliminates backpropagation for large language models.

Probabilistic graphical models are graphical representations of probability distributions. Graphical models have applications in many fields including biology, social sciences, linguistic, neuroscience. In this paper, we propose directed acyclic graphs (DAGs) learning via bootstrap aggregating. The proposed procedure i…

A new tensor-based method improves multi-dimensional data classification accuracy.

A new GAN model $α$-GAN with tunable loss function addresses gradient vanishing and mode collapse issues.

We investigate task clustering for deep-learning based multi-task and few-shot learning in a many-task setting. We propose a new method to measure task similarities with cross-task transfer performance matrix for the deep learning scenario. Although this matrix provides us critical information regarding similarity betw…

Introduces LoCA regret to evaluate model-based RL methods.