arXiv research

Gatherings of thousands to millions of people frequently occur for an enormous variety of events, and automated counting of these high-density crowds is useful for safety, management, and measuring significance of an event. In this work, we show that the regularly accepted labeling scheme of crowd density maps for trai…

TASFAR adapts regression models without labeled source data.

This work introduces a new method for coupling base and target densities in generative models.

We study the task of unsupervised domain adaptation, where no labeled data from the target domain is provided during training time. To deal with the potential discrepancy between the source and target distributions, both in features and labels, we exploit a copula-based regression framework. The benefits of this approa…

Improved OOD detection using label smoothing and k-NN density estimates.

This paper introduces PM and PMLP to enhance SSL by considering probability density and cluster assumptions.

Lower bound proves ridgeless regression performs poorly near interpolation threshold.

New GPU-based algorithm for fast optimal transport on brain tractograms.

We propose a supervised anomaly detection method based on neural density estimators, where the negative log likelihood is used for the anomaly score. Density estimators have been widely used for unsupervised anomaly detection. By the recent advance of deep learning, the density estimation performance has been greatly i…

Develops spherical density-equalizing maps for closed surfaces.

New method uses SoS densities and α-divergences for efficient sequential transport maps.

To reduce the label complexity in Agnostic Active Learning (A^2 algorithm), volume-splitting splits the hypothesis edges to reduce the Vapnik-Chervonenkis (VC) dimension in version space. However, the effectiveness of volume-splitting critically depends on the initial hypothesis and this problem is also known as target…

Study reveals how data density affects similarity learning in noisy conditions.

Given a data set and a subset of labels the problem of semi-supervised learning on point clouds is to extend the labels to the entire data set. In this paper we extend the labels by minimising the constrained discrete $p$-Dirichlet energy. Under suitable conditions the discrete problem can be connected, in the large da…

Proposes DISCO, the first CVI for density-based clustering with noise.

Developed an ellipsoidal density-equalizing map for genus-0 closed surfaces.

This paper shows stable mappings are never dense on non-compact manifolds.

The paper explores density of stable mappings and their properties.

The study provides homological characterizations for $Q$-manifolds and $l_2$-manifolds.

In this paper, we are concerned with the problem of creating flattening maps of simply-connected open surfaces in $\mathbb{R}^3$. Using a natural principle of density diffusion in physics, we propose an effective algorithm for computing density-equalizing flattening maps with any prescribed density distribution. By var…

Algorithm aligns 3D density maps using Wasserstein distance.

Method flattens complex surfaces with consistent density and shape.

This work reveals how label noise can cause a final ascent in neural network performance curves.

Develops conformal Bayes for two-sided censored Gaussian regression under label shift.

Non-compact manifolds prevent $C^0$-stable mappings from being dense.

Transformer with denoising diffusion improves probabilistic density estimation.

Study shows density of mapping classes on infinite-type surfaces using quasi-conformal maps.

Transfer learning has recently attracted significant research attention, as it simultaneously learns from different source domains, which have plenty of labeled data, and transfers the relevant knowledge to the target domain with limited labeled data to improve the prediction performance. We propose a Bayesian transfer…

The paper proposes a method to reliably select design algorithms for machine learning-guided design tasks.

We study the homotopical minimal periods for maps on infra-solvmanifolds of type (R) using the density of the homotopical minimal period set in the natural numbers. This extends the result of [10] from flat manifolds to infra-solvmanifolds of type (R). Applying our main result we will list all possible maps on infra-so…

We investigate the ability of popular flow based methods to capture tail-properties of a target density by studying the increasing triangular maps used in these flow methods acting on a tractable source density. We show that the density quantile functions of the source and target density provide a precise characterizat…

The paper classifies biharmonic quadratic maps between spheres, proving their energy density properties.

Concept drift in learning and classification occurs when the statistical properties of either the data features or target change over time; evidence of drift has appeared in search data, medical research, malware, web data, and video. Drift adaptation has not yet been addressed in high dimensional, noisy, low-context d…

Proposes MGPLL for PL learning with non-random noise.

Kernel density matrices simplify probabilistic deep learning.

RoPAWS improves semi-supervised learning on uncurated data.

In this paper, we introduce a new energy density function $\mathscr Y$ on the projective bundle $\mathbb{P}(T_M)\>M$ for a smooth map $f:(M,h)\>(N,g)$ between Riemannian manifolds $\mathscr Y=g_{ij}f^i_αf^j_β\frac{W^αW^β}{\sum h_{γδ} W^γW^δ}.$ We get new Hessian estimates to this energy density and obtain various new…

Develops NPMC method for noisy labels, improving multiclass classification accuracy.

We prove that the marginal densities of a global probability mass function in a primal normal factor graph and the corresponding marginal densities in the dual normal factor graph are related via local mappings. The mapping depends on the Fourier transform of the local factors of the models. Details of the mapping, inc…

Crowd counting problem aims to count the number of objects within an image or a frame in the videos and is usually solved by estimating the density map generated from the object location annotations. The values in the density map, by nature, take two possible states: zero indicating no object around, a non-zero value i…

Study on JNR monopoles, focusing on their spectral curves and energy density.

Recently, some works have suggested methods to combine variational probabilistic inference with Monte Carlo sampling. One promising approach is via local optimal transport. In this approach, a gradient steepest descent method based on local optimal transport principles is formulated to transform deterministically point…

A new method avoids partition function computation for Gibbs density estimation.

Partial multi-label learning (PML), which tackles the problem of learning multi-label prediction models from instances with overcomplete noisy annotations, has recently started gaining attention from the research community. In this paper, we propose a novel adversarial learning model, PML-GAN, under a generalized encod…

New approach predicts event probabilities for better event detection.

Network Embeddings (NEs) map the nodes of a given network into $d$-dimensional Euclidean space $\mathbb{R}^d$. Ideally, this mapping is such that `similar' nodes are mapped onto nearby points, such that the NE can be used for purposes such as link prediction (if `similar' means being `more likely to be connected') or c…

An image pattern can be represented by a probability distribution whose density is concentrated on different low-dimensional subspaces in the high-dimensional image space. Such probability densities have an astronomical number of local modes corresponding to typical pattern appearances. Related groups of modes can join…

Paper develops polynomial approximations for complex probability densities.