New neural network reduces CT radiation, works for any ROI size.
problem CT ROI reconstruction suffers from cupping artifacts and high computation.
method Two neural networks: one learns ROI-specific artifacts, the other learns DBP inversion.
result New network outperforms existing methods for any ROI size.
Interior tomography for the region-of-interest (ROI) imaging has advantages of using a small detector and reducing X-ray radiation dose. However, standard analytic reconstruction suffers from severe cupping artifacts due to existence of null space in the truncated Radon transform. Existing penalized reconstruction meth…
Study benchmarks machine learning for removing EEG artifacts.
problem Removing artifacts from EEGs to improve clinical interpretation.
method Applied various machine learning algorithms to a large artifact recognition dataset.
result Established a benchmark for future research on artifact removal.
Study cup products on CAT(0) cube complexes, proving quasimorphisms' vanishing results.
problem Understanding cup products in higher bounded cohomology groups.
method Extending vanishing results from Brooks quasimorphisms to median quasimorphisms on CAT(0) cube complexes.
result Vanishing results for cup products of median quasimorphisms on CAT(0) cube complexes.
Single CNN removes multiple ultrasound artifacts.
problem Efficiently remove multiple ultrasound artifacts.
method OT-driven multi-domain unsupervised deep learning.
result Single neural network removes various artifacts.
Study examines how image artifacts impact polyp detection and proposes methods to mitigate their effects.
problem Impact of image artifacts on automated polyp detection accuracy.
method Systematic analysis of six artifact classes, investigation of learning without forgetting framework.
result Artifacts can either benefit or harm polyp detection; learning without forgetting can mitigate some harmful effects.
New method corrects motion artifacts in MR images without paired data.
problem Lack of paired data for supervised training in deep learning for MR motion correction.
method Outlier-rejecting bootstrap subsampling and aggregation, using optimal transport cycleGAN.
result Outperforms existing deep learning methods in correcting motion artifacts from TSM.
CupNet prunes neural nets for cup-shaped data.
problem Pruning neural networks for cup-shaped data.
method Used simulated cup drawing data to prune a neural network.
result Pruning effectively reduces network size for cup-shaped data.
Let two Heegaard splittings V1∪W1 and V2∪W2 of a 3-manifold M be given. We consider the union stabilization M=V∪W which is a common stabilization of V1∪W1 and V2∪W2 having the property that V=V1∪V2. We show that any two Heegaard splittings of a 3-manifold have a uni…
Voice conversion (VC) aims at conversion of speaker characteristic without altering content. Due to training data limitations and modeling imperfections, it is difficult to achieve believable speaker mimicry without introducing processing artifacts; performance assessment of VC, therefore, usually involves both speaker…
Formula for computing triple-cup product from Heegaard diagrams of 3-manifolds.
problem Computing the triple-cup product invariant of 3-manifolds.
method Explicit formula from Heegaard diagrams and reduction of Turaev's homotopy intersection form.
result Triple-cup product can be recovered from Heegaard diagrams and Turaev's form.
New method compares geometric and standard cup products.
problem Reconciling partially defined and fully defined cochain products.
method Vector field flow through cubulation to compare products.
result Explicit cochain level comparison between intersection and cup products.
Deep learning method reduces conebeam artifacts in CT imaging.
problem Conebeam artifacts in CT imaging due to cone angle.
method Differentiated backprojection domain deep learning for data-driven inversion.
result Our method outperforms existing iterative methods with reduced runtime complexity.
Proposes a fixed smooth convolutional layer to reduce checkerboard artifacts in CNNs.
problem Checkerboard artifacts in CNNs during upsampling and strided convolution.
method Fixed convolutional layer with adjustable smoothness, applied to four CNNs and GANs.
result Significantly improves classification performance and image generation quality.
Study geodesic X-ray transform and streaking artifacts on simple surfaces or spaces of constant curvature.
problem Streaking artifacts in CT images due to metal regions.
method Geodesic X-ray transform on nontrapping compact Riemannian manifolds with strictly convex boundaries.
result Streaking artifacts result from conormal singularities along common tangent geodesics.
Relative cup-length defined for non-Morse functions on manifolds.
problem Defining a lower bound on critical points of non-Morse functions.
method Using local Morse cohomology and cohomology of isolating neighborhoods.
result A lower bound on critical points stronger than absolute cup-length.
Paper introduces adversarial lossy compression for video artifacts reduction.
problem Unpleasant reconstruction artifacts in standard video coding schemes at low bit-rates.
method Adversarial lossy video compression model minimizing an adversarial distortion objective.
result Reduction of perceptual artifacts and detail reconstruction under extreme compression.
Partial-input models fail to detect dataset artifacts, even when they perform poorly.
problem The effectiveness of partial-input models in detecting dataset artifacts is questionable.
method Design artificial datasets and identify trivial patterns in the SNLI dataset.
result Partial-input models can solve examples previously considered hard, indicating potential dataset artifacts.
The paper shows how to transform certain 3-manifold Heegaard splittings into simpler forms.
problem Weakly reducible Heegaard splittings with limited compression disks.
method Untelescoping of Heegaard splittings to simplify structures.
result Transformed splittings have fewer compression disks and clearer structures.
A new unsupervised method removes CT metal artifacts using beta-CycleGAN and attention.
problem Metal artifact reduction in computed tomography (CT) images.
method Unsupervised learning using a beta-CycleGAN architecture with attention mechanism.
result Improved metal artifact removal that preserves image details.
Let T be a separating incompressible torus in a 3-manifold M. Assuming that a genus g Heegaard splitting V∪SW can be positioned nicely with respect to T (e.g. V∪SW is strongly irreducible), we obtain an upper bound on the number of stabilizations required for V∪SW to become isotopic to a…
Glaucoma is the second leading cause of blindness all over the world, with approximately 60 million cases reported worldwide in 2010. If undiagnosed in time, glaucoma causes irreversible damage to the optic nerve leading to blindness. The optic nerve head examination, which involves measurement of cup-to-disc ratio, is…
A hybrid machine learning model predicts soccer match scores for FIFA Women's World Cups.
problem Forecasting soccer match scores for FIFA Women's World Cups.
method Combining bookmaker consensus and team strength parameters in a random forest model.
result The model favors the defending champion USA over the host France.
Single model corrects JPEG artifacts for various compression settings.
problem JPEG compression artifacts due to aggressive quantization.
method Parameterized architecture using quantization matrix.
result State-of-the-art performance across different quality settings.
Accelerated magnetic resonance (MR) scan acquisition with compressed sensing (CS) and parallel imaging is a powerful method to reduce MR imaging scan time. However, many reconstruction algorithms have high computational costs. To address this, we investigate deep residual learning networks to remove aliasing artifacts …
Our main result offers a new (quite systematic) way of deriving bounds for the cup-length of Poincare spaces over fields; we outline a general research program based on this result. For the oriented Grassmann manifolds, already a limited realization of the program leads, in many cases, to the exact values of the cup-le…
It follows from a theorem of Gromov that the stable systolic category of a closed manifold is bounded from below by the rational cup-length of the manifold. In the paper we study the inequality in the opposite direction. In particular, combining our results with Gromov's theorem, we prove the equality of stable systoli…
Let M=H+∪SH− be a genus g Heegaard splitting with Heegaard distance n≥κ+2: (1) Let c1, c2 be two slopes in the same component of ∂−H−, such that the natural Heegaard splitting Mi=H+∪S(H−∪ci2−handle) has distance less than n, then the distance…
Uniform criterion for vanishing products in bounded cohomology.
problem Vanishing of cup products and Massey products in bounded cohomology.
method Uniform vanishing criterion for products in bounded cohomology.
result Reproved and extended previous vanishing results.
Proves cup product homomorphism for bounded cohomology on negatively curved manifolds.
problem Understanding cup product behavior in bounded cohomology.
method Analyzes map Ψ* associating closed forms to bounded cohomology classes via integration.
result Proves Ψ* preserves cup product in sufficiently high degrees.
Paper tackles depth estimation and optic disc-cup segmentation from color fundus images.
problem Depth estimation and optic disc-cup segmentation from color fundus images.
method Uses fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation.
result Demonstrates improved accuracy in depth estimation and optic disc-cup segmentation.
Paper explores unsupervised learning for ultrasound image artifact removal.
problem Improving visual quality of ultrasound images from various artifacts.
method Inspired by optimal transport cycleGAN, unsupervised deep learning for artifact removal.
result Unsupervised learning method provides comparable results to supervised learning.
Study shows exact forms in bounded cohomology are in radical of cup product.
problem Understanding bounded cohomology of negatively curved manifolds.
method Integrating 2-forms over simplices to define bounded cocycles and studying cup products.
result Exact forms in bounded cohomology are in the radical of the cup product.
Extends Gromov's optimal systolic inequality to manifolds with specific cohomology properties.
problem Finding optimal systolic inequalities for manifolds with complex cohomology structures.
method Extends Gromov's inequality to manifolds with fundamental cohomology classes as cup products of 2-dimensional classes.
result Provides an optimal systolic inequality for a new class of manifolds.
Interpretation of electroencephalogram (EEG) signals can be complicated by obfuscating artifacts. Artifact detection plays an important role in the observation and analysis of EEG signals. Spatial information contained in the placement of the electrodes can be exploited to accurately detect artifacts. However, when few…
Geometrically interprets cup products and defines combinatorial Pin structures.
problem Understanding Steenrod's cup products and their geometric interpretation.
method Constructs vector fields and combinatorial frames to interpret cochain-level formulas.
result Geometrically interprets cup products and defines Pin structures combinatorially.
Paper compresses neural network weight-updates for image artifacts removal.
problem Efficiently compressing neural network weight-updates for image artifacts removal.
method Fine-tuning a pre-trained artifact removal network on target data with a compression objective that encourages sparse and quantized weight-updates.
result Achieves reconstruction quality comparable to traditional codecs at comparable bitrates.
L-CNNs approximate gauge actions, revealing fixed points with no lattice artifacts.
problem Approximating gauge actions with lattice artifacts.
method Lattice gauge-equivariant convolutional neural networks (L-CNNs).
result L-CNNs provide fixed point actions with no lattice artifacts.
Fan tokens surged before World Cup matches, but declined during them, revealing cognitive biases.
problem Analyzing the impact of FIFA World Cup matches on fan tokens.
method Event study and intraday analysis of blockchain-based fan tokens.
result Fan tokens experienced a surge in returns six months before the World Cup, followed by a decline during the matches, revealing asymmetries in performance.
Generative model predicts menstrual cycle lengths accounting for self-tracking artifacts.
problem Uncertainty in self-tracked health data due to user adherence.
method Hierarchical, generative model using machine learning.
result Model yields state-of-the-art performance in predicting menstrual cycle lengths.
We prove the vanishing of the cup product of the bounded cohomology classes associated to any two Brooks quasimorphisms on the free group. This is a consequence of the vanishing of the square of a universal class for tree automorphism groups.
New invariant connects virtual and classical linking numbers.
problem Linking numbers and virtual links.
method Introducing a quandle invariant Qtc(L) that preserves linking properties. result Invariant Qtc(L) is a quandle invariant that preserves linking properties. Estimates support in distributions with sampling artifacts and errors.
problem Support estimation in the presence of sampling artifacts and errors.
method Regularized weighted Chebyshev approximations with Touchard polynomials, discretized semi-infinte programming.
result Significant improvements over noiseless support estimation methods.
Let n, q and r be positive integers, and let KNn be the n-skeleton of an (N−1)-simplex. We show that for N sufficiently large every embedding of KNn in R2n+1 contains a link L1∪⋯∪Lr consisting of r disjoint n-spheres, such that the linking number link(Li,Lj) is …
We construct cup and cap products in intersection (co)homology with field coefficients. The existence of the cap product allows us to give a new proof of Poincare duality in intersection (co)homology which is similar in spirit to the usual proof for ordinary (co)homology of manifolds.
We give a complete calculation of the infinity flavor of Heegaard Floer homology with mod 2 coefficients for all three-manifolds and torsion Spin^c structures. The computation agrees with the conjectured calculation of Ozsvath and Szabo. This therefore establishes an isomorphism with Mark's cup homology mod 2.
NTK reveals order and chaos in DNNs, affecting checkerboard and border artifacts.
problem Checkerboard and border artifacts in DNNs.
method Analysis using Neural Tangent Kernel (NTK) in infinite-width setting.
result Transition between order and chaos regimes affects DNN performance.
Extended systolic inequality for 2-complexes to improve group systolic area bounds.
problem Improving bounds on systolic area of various groups.
method Extended systolic inequality for piecewise Riemannian 2-complexes.
result Improved universal lower bound for systolic area of many groups.