Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

129258386515 · Jun 202019922001200920172026
48 results for Intersection over Union (IoU)

This short article aims at demonstrate that the Intersection over Union (or Jaccard index) is not a submodular function. This mistake has been made in an article which is cited and used as a foundation in another article. The Intersection of Union is widely used in machine learning as a cost function especially for imb…

2018-09-03abs ↗pdf ↗

Algorithm generates adaptive confidence sets for instance segmentation with guaranteed coverage.

problem Uncalibrated predictions and lack of uncertainty quantification in instance segmentation models.
method Conformal prediction algorithm to generate adaptive confidence sets with provable guarantees.
result Empirically, prediction sets vary in size based on query difficulty and attain target coverage, outperforming baselines.

Bayesian variational inference improves medical image segmentation confidence.

problem Improving interpretability and confidence in deep learning models for medical image segmentation.
method Encoder-decoder architecture based on variational inference for segmenting brain tumor images.
result The model segments brain tumors with both aleatoric and epistemic uncertainty.

RankSEG-RMA improves semantic segmentation efficiency and applicability.

problem Inconsistent or suboptimal semantic segmentation results due to argmax or thresholding.
method Developed RankSEG-RMA using reciprocal moment approximation to optimize Dice and IoU metrics.
result RankSEG-RMA reduces computational complexity to O(d) while maintaining comparable performance.

Deep Convolutional Neural Networks (DCNNs) are used extensively in medical image segmentation and hence 3D navigation for robot-assisted Minimally Invasive Surgeries (MISs). However, current DCNNs usually use down sampling layers for increasing the receptive field and gaining abstract semantic information. These down s…

2019-01-26abs ↗pdf ↗

Accurate volume segmentation from the Computed Tomography (CT) scan is a common prerequisite for pre-operative planning, intra-operative guidance and quantitative assessment of therapeutic outcomes in robot-assisted Minimally Invasive Surgery (MIS). 3D Deep Convolutional Neural Network (DCNN) is a viable solution for t…

2019-09-16abs ↗pdf ↗

AI tool automates blood segmentation from head CT scans after SAH.

problem Accurate volumetric assessment of SAH patients for clinical and prognostic implications.
method Transformer-based Swin UNETR architecture for noncontrast CT scans.
result High accuracy and robust performance across internal and external validation cohorts.

TokenCut detects and segments objects in images and videos without supervision.

problem Detecting and segmenting salient objects in images and videos without labeled data.
method Graph-based approach using self-supervised transformer features and Normalized Cut algorithm.
result Achieves state-of-the-art results on various detection and segmentation tasks.

The following problem was proposed in 2010 by S. Lando. Let MM and NN be two unions of the same number of disjoint circles in a sphere. Do there always exist two spheres in 3-space such that their intersection is transversal and is a union of disjoint circles that is situated as MM in one sphere and as NN in the ot…

2012-10-27abs ↗pdf ↗

A new framework for consistent segmentation evaluation reduces operating losses.

problem Inconsistent thresholding-based segmentation methods lead to suboptimal solutions.
method Developed a consistent ranking-based framework (RankDice/RankIoU) using Bayes rules and Dice-/IoU-calibration.
result The proposed framework is Dice-/IoU-calibrated and provides excess risk bounds and convergence rates.

Formula for volumes of odd strata of quadratic differentials using graph intersection numbers.

problem Calculating volumes of specific strata of quadratic differentials.
method Expressed volumes as a sum over stable graphs, with coefficients as intersection numbers of psi classes with combinatorial classes.
result Formula for volumes of odd strata of quadratic differentials.

Accurate estimation of the positions and shapes of microscale objects is crucial for automated imaging-guided manipulation using a non-contact technique such as optical tweezers. Perception methods that use traditional computer vision algorithms tend to fail when the manipulation environments are crowded. In this paper…

2019-07-03abs ↗pdf ↗

The paper defines and proves stabilization for 3-manifold decompositions with multibranched surface intersections.

problem Decomposing 3-manifolds with more than 3 handlebodies and multibranched surface intersections.
method Definition and proof of stabilization operations for these decompositions.
result Stable equivalence of handlebody decompositions with multibranched surface intersections.

Let XX be a contractible 22-complex which is a union of two contractible subcomplexes YY and Z.Z. Is the intersection YZY\cap Z contractible as well? In this note, we prove that the inclusion-induced map π1(YZ)π1(Z)π_{1}(Y\cap Z)\rightarrow π_{1}(Z) is injective if YY is π1π_{1}-injective subcomplex in a locally CAT(0) 2-co…

2018-10-16abs ↗pdf ↗

We study the way a strongly irreducible Heegaard surface ΣΣ intersects a knot exterior XX embedded in a 3-manifold, and show that if ΣXΣ\cap \partial X consists of simple closed curves which are essential in both ΣΣ and X\partial X, then the intersection XΣX \cap Σ consists of meridional annuli only. As an applicat…

2002-06-09abs ↗pdf ↗

Ancient solutions and translators identified for Lagrangian flow.

problem Characterizing ancient solutions and translators of Lagrangian mean curvature flow.
method Analyzing almost calibrated, exact, ancient solutions with specific geometric properties.
result All ancient solutions with entropy less than 3 are special Lagrangian, planes, or translators in \(\mathbb{C}^2\).

A benchmark evaluates ioUS-to-MR synthesis methods for brain tumor surgery.

problem Difficult interpretation of ioUS images for brain tumor surgery.
method Six generators trained under four inference regimes and two targets on public data.
result SynDiff-2.5D best preserved downstream segmentation (U_Dice=0.55).

SCENE-Net improves 3D point cloud segmentation with low resource usage and transparency.

problem Lack of resources and transparency in 3D semantic segmentation models.
method SCENE-Net uses signature shapes identified via GENEOs to achieve semantic segmentation with minimal resources.
result SCENE-Net achieves comparable IoU to state-of-the-art methods with less data and computational resources.

Joyce's criterion for sLag smoothings extended to non-compact, non-transverse intersections.

problem Existence of special Lagrangian smoothings for non-compact, non-transverse intersections.
method Leung-Yau-Zaslow transform, deformed Hermitian Yang-Mills connections, Calabi ansatz, mean curvature flow, Bridgeland stability conditions.
result Existence of sLag smoothings on stable loci with slope inequality.

We are interested in contractible n-manifolds M which "split" as M = A union B where A,B, and A intersect B are all homeomorphic to Euclidean n-space (such M are called open n-splitters) or A,B, and A intersect B are all homeomorphic to the n-dimensional unit ball (such M are called closed n-splitters). We introduce a …

2015-02-11abs ↗pdf ↗

Gay and Kirby introduced trisections which describe any closed oriented smooth 4-manifold XX as a union of three four-dimensional handlebodies. A trisection is encoded in a diagram, namely three collections of curves in a closed oriented surface ΣΣ, guiding the gluing of the handlebodies. Any morphism φ\varphi from …

2019-01-15abs ↗pdf ↗

Graph Laplacians adapt to different manifold dimensions, while Dirichlet energies converge to a tensorized Dirichlet energy.

problem Understanding machine learning methods for data with varying intrinsic dimensions.
method Γ-convergence of graph Dirichlet energies and spectral convergence of graph Laplacians on intersecting manifolds of varying dimensions.
result Normalized Dirichlet energy converges to a tensorized Dirichlet energy that adapts to all dimensions simultaneously.

The SO(3)-monopole program, initiated by Pidstrigatch and Tyurin [arXiv:dg-ga/9507004], yields a relationship between the Donaldson and Seiberg-Witten invariants through a cobordism between the moduli spaces defining these invariants. The main technical difficulty in this program lies in describing the links of singula…

2012-11-02abs ↗pdf ↗

CITE algorithm provides anytime-valid certification of model outputs.

problem Challenges in controlling error levels in LLM self-consistency.
method Certification by Intersection-union Testing with E-processes (CITE) algorithm.
result Provable control of false certification at any prescribed level under arbitrary stopping rules.

We propose a novel approach for semantic segmentation that uses an encoder in the reverse direction to decode. Many semantic segmentation networks adopt a feedforward encoder-decoder architecture. Typically, an input is first downsampled by the encoder to extract high-level semantic features and continues to be fed for…

2019-08-22abs ↗pdf ↗

Study intersection homotopy groups in coarsenings of CS sets.

problem Understanding invariance of intersection homotopy groups in coarsenings of CS sets.
method Introduced a general perversity and its pushforward, established invariance theorems for intersection homotopy groups in coarsenings of CS sets.
result Found invariance theorems for intersection homotopy groups in coarsenings of CS sets.

The analysis of scientific data of increasing size and complexity requires statistical machine learning methods that are both interpretable and predictive. Union of Intersections (UoI), a recently developed framework, is a two-step approach that separates model selection and model estimation. A linear regression algori…

2018-08-21abs ↗pdf ↗

Counting meanders on surfaces of arbitrary genus, with precise asymptotics.

problem Counting and understanding meanders on surfaces of arbitrary genus.
method Square-tiled surfaces, moduli spaces of Abelian and quadratic differentials, Witten-Kontsevich 2-correlators.
result Asymptotic probability and polynomial growth of meanders with intersections.

Uniformly Euclidean metrics with isolated singularities on certain manifolds are Ricci flat and have nonnegative synthetic Ricci curvature.

problem Proving the existence of Ricci flat metrics with isolated singularities on specific manifolds.
method Demonstrating nonnegative synthetic Ricci curvature using the RCD(0, n) condition.
result Uniformly Euclidean metrics with isolated singularities on Mn=Tn#M0M^n = T^n \# M_0 are Ricci flat and extend smoothly over the singularity.

The study explores convex unions and completions in simplicial pseudomanifolds, revealing unexpected behavior.

problem Understanding the behavior of convex unions in simplicial pseudomanifolds.
method Generalization to simplicial pseudomanifolds, considering PL homeomorphisms and edge subdivisions.
result Unexpected behavior in convex unions and completions, including empty contraction spaces and large/small contraction spaces.

A knot K in 1-bridge position with respect to a genus-g Heegaard surface in a 3-manifold can be moved by isotopy through knots in 1-bridge position until it lies in a union of n parallel genus-g surfaces tubed together by n-1 straight tubes, with K intersecting each tube in two arcs connecting the ends. We prove that t…

2009-01-11abs ↗pdf ↗

Let G be a (real or complex) linear reductive algebraic group acting on an affine variety V. Let W be a subvariety. In this work we study how the G-orbits intersect W. We develop a criterion to determine when the intersection can be described as a finite union of orbits of a reductive subgroup. The conditions of the cr…

2008-10-31abs ↗pdf ↗

We consider the "partial information decomposition" (PID) problem, which aims to decompose the information that a set of source random variables provide about a target random variable into separate redundant, synergistic, union, and unique components. In the first part of this paper, we propose a general framework for …

2019-08-23abs ↗pdf ↗