SCOREBED isolates EIG double intractability in a policy-independent score-matching stage, then trains design policies with a singly intractable gradient estimator, enabling cheap multi-policy selection.
Mixed citations
U-Net: Convolutional networks for biomedical image segmentation,
Mixed citation behavior. Most common role is background (50%).
56
Pith papers citing it
56.5k
external citations · Crossref
Background
50% of classified citations
citation-role summary
background 3
method 2
baseline 1
citation-polarity summary
authors
co-cited works
representative citing papers
A new quality-guided approach for semi-supervised medical image segmentation that trains a predictor on synthetic errors to enhance pseudolabel handling.
GPROF-IR is a CNN-based retrieval that uses temporal context in geostationary IR observations to produce precipitation estimates with lower error than prior IR methods and climatological consistency with PMW retrievals for integration into IMERG V08.
AttentionBender applies 2D transforms to cross-attention maps in video diffusion transformers, producing distributed distortions and glitch aesthetics that reveal entangled attention mechanisms while serving as both an XAI probe and creative tool.
A LoRA-adapted conditional diffusion surrogate for electromagnetic calorimeter showers matches key observables within 2% RMSE and reproduces directional trends in design-utility gradients.
OOD-SEG reframes multi-class segmentation from sparse positive-only annotations as pixel-wise positive-unlabelled learning solved by integrating out-of-distribution detection techniques, with a proposed cross-validation evaluation on surgical imaging datasets.
Proposes a cyclic 2.5D perceptual loss with manufacturer SUVR standardization for T1w MRI to tau PET synthesis, reporting improved regional agreement on ADNI and SCAN cohorts across U-Net, UNETR, SwinUNETR, CycleGAN, and Pix2Pix.
STREAM decouples text (via AdaLN) from music (via energy-based BEAM attention) to generate editable, musically aligned dance motions with a new annotated dataset and editability metric.
X-ray diffraction reveals that charge localization in EuAl4 is enhanced by magnetic ordering and can be reversibly tuned by applying uniaxial pressure along different crystal axes.
FRPDF, a full-resolution progressive dilated fusion recurrent network trained solely on synthetic rasters, extracts rail-top and track centerlines from classified MLS point clouds.
DeepMine-Mamba adds an Anti-Dilution Gate to Mamba-based models to counteract feature dilution in document binarization and reports competitive FM and Fps scores on DIBCO benchmarks under leave-one-year-out evaluation.
High magnetic fields directly enhance the amplitude and correlation length of stripe order in a cuprate superconductor far above the vortex melting transition, indicating a coupling mechanism independent of superconductivity suppression.
CrackGeoFM is a multi-task framework that adapts a frozen visual foundation model with FCEM, CFAM, and SMTD modules for crack mask prediction, skeleton reconstruction, and uncertainty estimation, reporting SOTA results across 20 datasets including few-shot settings.
PaNO neural operator improves port-power readout fidelity in photonic design surrogates over global-field baselines on a 3x3 MMI benchmark.
ARC-STAR reduces velocity rollout error by at least 36x over raw Poseidon across all tested regime cells via auditable global and local correction stages on five flow benchmarks.
A Jacobian sensitivity curve computed at initialization identifies the narrowest U-Net configuration that avoids performance collapse, matching nnU-Net accuracy with 400-1600x fewer parameters on six medical datasets.
Commutativity regularization mitigates transient error amplification in autoregressive neural simulators by penalizing non-normality and non-commutativity of Jacobians, yielding stable long-horizon rollouts.
Spectral analysis of activations and gradients provides new diagnostics that link batch size to representation geometry, early covariance tails to token efficiency, and spectral shifts to learning dynamics in decoder-only LLMs, backed by a mechanistic model.
A recurrent Vision Transformer hypernetwork injects context into Flux Neural Operators to infer and solve unseen conservation laws while preserving robustness and long-time stability.
SIAM achieves state-of-the-art whole-head MRI segmentation of 16 structures including extra-cerebral tissues by training on synthetic data from just six manual templates, matching or exceeding prior methods on 301 scans across eight heterogeneous datasets.
Cross-domain transfer of remote-sensing HSI foundation models improves proximal sensing semantic segmentation over in-domain training and narrows the gap to cross-modality methods on the HS3-Bench benchmark.
VSLP infers dense segmentations from global label proportions via a pre-trained transformer for initial confidence maps followed by variational optimization using Wasserstein fidelity and a learned regularizer, outperforming prior weakly supervised methods on histopathology datasets.
The ICPR 2026 LRLPR competition on real low-quality license plate images drew 99 valid submissions, with the winning team reaching 82.13% recognition rate and four teams exceeding 80%.
A tornado outbreak with simultaneous tornadic supercells occurred in the Philippines within an easterly severe weather regime, documented as the first known instance there.
citing papers explorer
-
Bayesian Experimental Design via Score Matching
SCOREBED isolates EIG double intractability in a policy-independent score-matching stage, then trains design policies with a singly intractable gradient estimator, enabling cheap multi-policy selection.
-
Quality-Guided Semi-Supervised Learning for Medical Image Segmentation
A new quality-guided approach for semi-supervised medical image segmentation that trains a predictor on synthetic errors to enhance pseudolabel handling.
-
GPROF-IR: An Improved Single-Channel Infrared Precipitation Retrieval for Merged Satellite Precipitation Products
GPROF-IR is a CNN-based retrieval that uses temporal context in geostationary IR observations to produce precipitation estimates with lower error than prior IR methods and climatological consistency with PMW retrievals for integration into IMERG V08.
-
AttentionBender: Manipulating Cross-Attention in Video Diffusion Transformers as a Creative Probe
AttentionBender applies 2D transforms to cross-attention maps in video diffusion transformers, producing distributed distortions and glitch aesthetics that reveal entangled attention mechanisms while serving as both an XAI probe and creative tool.
-
Differentiable Surrogate for Detector Simulation and Design with Diffusion Models
A LoRA-adapted conditional diffusion surrogate for electromagnetic calorimeter showers matches key observables within 2% RMSE and reproduces directional trends in design-utility gradients.
-
OOD-SEG: Exploiting out-of-distribution detection techniques for learning image segmentation from sparse multi-class positive-only annotations
OOD-SEG reframes multi-class segmentation from sparse positive-only annotations as pixel-wise positive-unlabelled learning solved by integrating out-of-distribution detection techniques, with a proposed cross-validation evaluation on surgical imaging datasets.
-
Cyclic 2.5D Perceptual Loss for Cross-Modal 3D Medical Image Synthesis: T1w MRI to Tau PET
Proposes a cyclic 2.5D perceptual loss with manufacturer SUVR standardization for T1w MRI to tau PET synthesis, reporting improved regional agreement on ADNI and SCAN cohorts across U-Net, UNETR, SwinUNETR, CycleGAN, and Pix2Pix.
-
Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Motion Generation
STREAM decouples text (via AdaLN) from music (via energy-based BEAM attention) to generate editable, musically aligned dance motions with a new annotated dataset and editability metric.
-
Strain-tunable charge localization coupled to complex magnetic orders in EuAl$_4$
X-ray diffraction reveals that charge localization in EuAl4 is enhanced by magnetic ordering and can be reversibly tuned by applying uniaxial pressure along different crystal axes.
-
Rail Track Extraction from Rasterized Classified Point Clouds Using a Full-Resolution, Fully Convolutional Recurrent Neural Network
FRPDF, a full-resolution progressive dilated fusion recurrent network trained solely on synthetic rasters, extracts rail-top and track centerlines from classified MLS point clouds.
-
DeepMine-Mamba: Mitigating Information Dilution in Mamba-Based State Space Models for Document Image Binarization
DeepMine-Mamba adds an Anti-Dilution Gate to Mamba-based models to counteract feature dilution in document binarization and reports competitive FM and Fps scores on DIBCO benchmarks under leave-one-year-out evaluation.
-
Direct High-Magnetic-Field Coupling to Stripe Order in a Cuprate Superconductor
High magnetic fields directly enhance the amplitude and correlation length of stripe order in a cuprate superconductor far above the vortex melting transition, indicating a coupling mechanism independent of superconductivity suppression.
-
Multi-Task Crack Foundation Model for Engineering-Reliable Crack Representation and Topology Preservation in Civil Infrastructure
CrackGeoFM is a multi-task framework that adapts a frozen visual foundation model with FCEM, CFAM, and SMTD modules for crack mask prediction, skeleton reconstruction, and uncertainty estimation, reporting SOTA results across 20 datasets including few-shot settings.
-
Will Accurate Fields Mislead Photonic Design? FromGlobal Accuracy to Port Readout
PaNO neural operator improves port-power readout fidelity in photonic design surrogates over global-field baselines on a 3x3 MMI benchmark.
-
ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models
ARC-STAR reduces velocity rollout error by at least 36x over raw Poseidon across all tested regime cells via auditable global and local correction stages on five flow benchmarks.
-
XTinyU-Net: Training-Free U-Net Scaling via Initialization-Time Sensitivity
A Jacobian sensitivity curve computed at initialization identifies the narrowest U-Net configuration that avoids performance collapse, matching nnU-Net accuracy with 400-1600x fewer parameters on six medical datasets.
-
Controlling Transient Amplification Improves Long-horizon Rollouts
Commutativity regularization mitigates transient error amplification in autoregressive neural simulators by penalizing non-normality and non-commutativity of Jacobians, yielding stable long-horizon rollouts.
-
Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization
Spectral analysis of activations and gradients provides new diagnostics that link batch size to representation geometry, early covariance tails to token efficiency, and spectral shifts to learning dynamics in decoder-only LLMs, backed by a mechanistic model.
-
A Robust Foundation Model for Conservation Laws: Injecting Context into Flux Neural Operators via Recurrent Vision Transformers
A recurrent Vision Transformer hypernetwork injects context into Flux Neural Operators to infer and solve unseen conservation laws while preserving robustness and long-time stability.
-
SIAM: Head and Brain MRI Segmentation from Few High-Quality Templates via Synthetic Training
SIAM achieves state-of-the-art whole-head MRI segmentation of 16 structures including extra-cerebral tissues by training on synthetic data from just six manual templates, matching or exceeding prior methods on 301 scans across eight heterogeneous datasets.
-
Cross-Domain Transfer of Hyperspectral Foundation Models
Cross-domain transfer of remote-sensing HSI foundation models improves proximal sensing semantic segmentation over in-domain training and narrows the gap to cross-modality methods on the HS3-Bench benchmark.
-
Semantic Segmentation for Histopathology using Learned Regularization based on Global Proportions
VSLP infers dense segmentations from global label proportions via a pre-trained transformer for initial confidence maps followed by variational optimization using Wasserstein fidelity and a learned regularizer, outperforming prior weakly supervised methods on histopathology datasets.
-
ICPR 2026 Competition on Low-Resolution License Plate Recognition
The ICPR 2026 LRLPR competition on real low-quality license plate images drew 99 valid submissions, with the winning team reaching 82.13% recognition rate and four teams exceeding 80%.
-
Localized Tornado Outbreak at the Upstream of a Tropical Easterly Wave in Camarines Norte, Philippines (13 September 2025)
A tornado outbreak with simultaneous tornadic supercells occurred in the Philippines within an easterly severe weather regime, documented as the first known instance there.
-
FlowForge: A Staged Local Rollout Engine for Flow-Field Prediction
FlowForge predicts flow fields via staged local updates with a shared lightweight predictor, matching or exceeding baselines in accuracy while improving robustness to noise and reducing latency.
-
Backbone-Conditional Behavior of Modality Gating in Multi-Modal Prostate MRI Segmentation: A 5-Fold Cross-Validation and Gate Mechanism Analysis
Modality gating is backbone-conditional: nnU-Net gates become static priors that degrade ranking score, while Mamba gates retain per-sample routing and improve it; only modality dropout helps both.
-
PSIRNet: Deep Learning-based Free-breathing Rapid Acquisition Late Enhancement Imaging
PSIRNet produces diagnostic-quality free-breathing PSIR LGE cardiac MRI from a single interleaved IR/PD acquisition over two heartbeats using a physics-guided deep learning network trained on over 800,000 slices.
-
Component-Adaptive and Lesion-Level Supervision for Improved Small Structure Segmentation in Brain MRI
CATMIL augments nnU-Net with component-adaptive Tversky and MIL-based lesion supervision to raise Dice scores, small-lesion recall, and error control on the MSLesSeg dataset.
-
RABC-Net: Reliability-Aware Annotation-Free Skin Lesion Segmentation for Low-Resource Dermoscopy
RABC-Net achieves 86.58% DICE and 79.47% JAC on skin lesion segmentation across ISIC-2017, ISIC-2018, and PH2 using only pseudo-labels and no manual masks for training or adaptation.
-
RSEdit: Text-Guided Image Editing for Remote Sensing
RSEdit adapts off-the-shelf text-to-image models into a collection of editing systems that follow text instructions while keeping geospatial structure intact in remote sensing images.
-
Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising
ASTERIS, a self-supervised spatiotemporal denoising algorithm, improves astronomical detection limits by 1 magnitude at 90% completeness while identifying three times more redshift >9 galaxy candidates in JWST images.
-
Algebraic Language Models for Inverse Design of Metamaterials via Diffusion Transformers
DiffuMeta uses diffusion transformers and algebraic language representations to generate diverse 3D shell metamaterials with targeted stress-strain responses under large deformations including buckling and contact.
-
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
Biased noise sampling for rectified flows combined with a bidirectional text-image transformer architecture yields state-of-the-art high-resolution text-to-image results that scale predictably with model size.
-
GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data Engine
GEAR-Seg decouples segmentation, semantic description, and LLM reasoning into an explicit chain for interpretable zero-shot reasoning segmentation while generating the GEAR-131K dataset.
-
MLFFM-SegDiff: A Multi-Level Feature Fusion Diffusion Model for Skin Lesion Segmentation
MLFFM-SegDiff adds a multi-level feature fusion module and dual-path encoder to a diffusion U-Net, reporting improved Jaccard (0.8546) and Dice (0.9207) scores over baselines on three skin lesion datasets.
-
Test-Time Adaptation in Optical Coherence Tomography Using Trajectory-Aligned Time-Independent Flow
Flow-matching TTA with histogram matching to synthetic reference trajectories and time-independent flow achieves SOTA segmentation of AMD biomarkers in OCT.
-
SegTME-UNI2: A Foundation Model-Based Framework for Generalisable Multiclass Cell Segmentation and LLM-Driven Tumour Microenvironment Characterisation in Histopathology
SegTME-UNI2 pairs a UNI2-based dual-head segmentation model trained via progressive pseudo-labeling with an LLM to produce multiclass cell maps and narrative TME descriptions from H&E images.
-
Reliability of Probabilistic Emulation of Physical Systems
CRPS-trained ensembles achieve better uncertainty reliability and speed than latent generative models for probabilistic emulation of 2D physical systems.
-
CDPM-Align: Multi-Scale Guidance-Aligned Diffusion Pretraining for Robust Few-Shot Anatomical Landmark Detection
CDPM-Align applies multi-scale guidance-aligned conditional diffusion pretraining on three small heterogeneous datasets to improve accuracy and uncertainty in few-shot (10-25 image) anatomical landmark detection.
-
Striding Across Reynolds Numbers: Representation Geometry in Neural PDE Generalisation
ConvAE-Relay retrieval via source-trained autoencoder latent matching achieves 38.34+/-0.07% relative L2 error on 10x Re shift using only source database, with U-Net at 34.72% and matching quality identified as dominant factor.
-
Physics-informed neural networks for quantitative assessment of cancellous bone microstructure from photoacoustic signals
Biot-PINN embeds Biot poroelasticity into a neural network to decode photoacoustic signals for cancellous bone microstructure grading at 97% accuracy.
-
Observation-Guided Neural Surrogate Learning for Scientific Simulation Emulation: A Single-Gauge Flood-Inundation Proof of Concept
An EnsCGP coarse surrogate plus U-Net-ASPP corrector emulates LISFLOOD-FP flood depths on a 256x256 grid around one Chicago gauge, achieving R² ≈ 0.99 and MAE < 0.01 m on held-out events while matching the gauge depth at that single pixel.
-
Weighted Knowledge Distillation for Semi-Supervised Segmentation of Maxillary Sinus in Panoramic X-ray Images
A semi-supervised framework using weighted knowledge distillation and SinusCycle-GAN refinement achieves 96.35% Dice score for maxillary sinus segmentation in panoramic X-rays from 2,511 patients.
-
Training-inference input alignment outweighs framework choice in longitudinal retinal image prediction
Training-inference input alignment outweighs framework choice for longitudinal retinal image prediction, with deterministic regression matching complex models when acquisition variability dominates disease progression.
-
Submanifold Sparse Convolutional Networks for Automated 3D Segmentation of Kidneys and Kidney Tumours in Computed Tomography
A two-stage sparse convolutional network pipeline for native high-resolution 3D kidney and tumor segmentation in CT that matches top Dice scores while reducing VRAM and runtime versus nnU-Net and SegVol.
-
Physics Priors Offer Useful Accuracy-Carbon Trade-Offs in Spatio-Temporal Forecasting
Stronger physics priors in neural networks for spatio-temporal shear flow forecasting yield substantially lower training carbon footprints than weak or no priors, though inference savings are less consistent.
-
HTC-SGA Former: A Hybrid Transformer-CNN Network with Self-Guided Attention and a New Boundary-Weighted Adaptive Loss for Coronary DSA Vessel Segmentation
HTC-SGA Former with MS-GLWA, SGFA, and BWACL beats 14 SOTA segmenters on private left/right coronary DSA subsets at 0.81M parameters.
-
PEFT-MedSAM: Efficient Fine-Tuning of Medical Foundation Models for Explainable Skin Lesion Segmentation
PEFT-MedSAM adapts MedSAM by training only its mask decoder on ISIC 2018 skin lesion data, achieving Dice 0.9411 and outperforming U-Net (0.8715) and zero-shot MedSAM (0.8997), with PH2 validation (0.9467) and 98.27% Grad-CAM pointing accuracy.
-
Do We Really Need Diffusion? A Fast U-Net for Paired Medical Image Translation
Lightweight U-Net outperforms DDPM on T2w-to-MRI-SFF translation (r=0.975 vs 0.962, MAE=0.014 vs 0.019) with 208x faster inference on 230k paired images from NAKO.
-
Patient-Level Diagnosis of Acute Myeloid Leukemia via Deep Learning Analysis of Bone Marrow Smear
YOLO segmentation plus EfficientNet classification aggregates cell predictions to patient-level CBLC ratios, reporting weighted F1 scores of 0.87-0.91 on three external center cohorts from 89 patients.