Hi-Seg achieves a mean Dice score of nearly 85% for pulmonary nodule segmentation by having humans iteratively refine prompts for the Segment Anything Model, outperforming standalone deep learning and SAM models on a large multi-center dataset.
hub Mixed citations
Attention U-Net: Learning Where to Look for the Pancreas
Mixed citation behavior. Most common role is background (56%).
72
Pith papers citing it
Background
56% of classified citations
abstract
We propose a novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes. Models trained with AGs implicitly learn to suppress irrelevant regions in an input image while highlighting salient features useful for a specific task. This enables us to eliminate the necessity of using explicit external tissue/organ localisation modules of cascaded convolutional neural networks (CNNs). AGs can be easily integrated into standard CNN architectures such as the U-Net model with minimal computational overhead while increasing the model sensitivity and prediction accuracy. The proposed Attention U-Net architecture is evaluated on two large CT abdominal datasets for multi-class image segmentation. Experimental results show that AGs consistently improve the prediction performance of U-Net across different datasets and training sizes while preserving computational efficiency. The code for the proposed architecture is publicly available.
hub tools
citation-role summary
background 7
baseline 1
method 1
citation-polarity summary
representative citing papers
AuraMask produces 40 aesthetic anti-facial recognition filters that match or exceed prior adversarial effectiveness and achieve significantly higher user acceptance in a 630-person study.
TopoU-Net is a rank-path U-Net for combinatorial complexes that encodes by lifting cochains upward along incidences, decodes by transporting downward, and merges via skip connections at matched ranks.
XAttnRes introduces cross-stage attention residuals that maintain a global feature history and selectively aggregate prior representations, improving medical image segmentation and performing on par with baselines even without skip connections.
GDLA delivers state-of-the-art accuracy on CT, MRI, ultrasound and dermoscopy segmentation benchmarks while keeping linear O(N) complexity in a PVT encoder-decoder.
Variational Regularization imposes an adaptive information bottleneck on noisy intermediate features in DP3-UNet and DP3-DiT policies, consistently raising task success rates on RoboTwin2.0, Adroit, and MetaWorld while achieving new state-of-the-art results.
S2M-Net achieves state-of-the-art Dice scores on 16 medical datasets across 8 modalities using a 4.7M-parameter spectral-spatial mixer and morphology-aware adaptive loss, outperforming transformers with 3.5-6x fewer parameters.
CurvSegFlow applies time-conditioned flow matching with a U-Net backbone and triple-term loss to progressively refine segmentations of thin structures in noisy images, reporting competitive performance on microtubule, vessel, and nerve datasets.
PU-UNet integrates stabilized product units into low-resolution residual blocks of a U-Net, reporting higher Dice scores than a matched residual U-Net baseline on ISIC 2018, Kvasir-SEG, and BUSI datasets with nearly identical parameters and latency.
EyeMVP learns OCT-informed CFP representations via cross-modal masked reconstruction on 674k paired triples and reports competitive or superior performance on 15 retinal classification and segmentation tasks.
A deep surrogate model learns coarse-grained dynamic aperture directly from suitably encoded one-turn maps by treating stability prediction as image segmentation and transfers to realistic EIC tracking.
MS-DKC is a dataset knowledge card framework that maps image, morphology, supervision, context, and risk descriptors to design priors and failure modes, shown to produce dataset-specific model adaptations with improved metrics on DRIVE, ISIC2018, and ACDC.
XSSR selects 5% of target samples via source-trained MAE embeddings and auto-calibrated greedy scoring to reach 99.3% of full-data Dice on chest X-ray and outperform random/CoreSet baselines on retinal and prostate MRI benchmarks.
BiSegMamba is a bidirectional tri-oriented Mamba architecture that improves performance and reduces FLOPs in 3D medical image segmentation across brain, cardiac, abdominal, and vascular tasks.
LegSegNet is the first public end-to-end deep learning system for lower extremity CT tissue segmentation and body composition quantification, reporting an average Dice score of 89.31 on held-out test slices.
K-U-KAN combines KAN feature lifting, Koopman linear dynamics, and U-KAN refinement with physical and geometric priors to reconstruct 3D dental anatomy from single panoramic radiographs, matching baselines on metrics while improving perceptual quality and halving training time.
StruMPL is a multi-task dense regression model that jointly addresses disjoint partial supervision, MNAR labels, and inter-task physical constraints for improved forest biomass estimation from Earth observation.
A spectral vision transformer achieves equitable or superior performance with fewer parameters than standard ViTs, CNNs, and other models by using spectral projections for tokenization in limited-data medical imaging.
A frequency-enhanced Vision Transformer with FDSA, FGMLP, WAFF, and FCSB modules delivers superior volumetric medical image segmentation performance and efficiency over prior state-of-the-art methods.
ESICA delivers state-of-the-art accuracy on a five-modality 3D medical segmentation benchmark while offering a compact variant with far fewer parameters.
Defines recoverability maps via dense synthetic degradation sweeps and two summary metrics to show AI restoration recovers license plates from ~93% of extreme angle parameter space, with geometry rather than model architecture as the binding limit.
SPD improves SAM segmentation robustness to noisy prompts by learning anatomical saliency priors, distilling consensus prompts from adjacent slices, and enforcing pairwise slice consistency.
SemBugger achieves polymorphic backdoors in semantic communication via graded-intensity trigger poisoning and hierarchical loss, plus a noise-based defense with a theoretical efficacy bound.
CDSA-Net decouples vascular structure extraction and background restoration in coronary DSA via hierarchical geometric priors and adaptive noise modeling to eliminate artifacts while preserving tissue fidelity.
citing papers explorer
-
CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing
The paper defines the Conformal Hallucination Estimation Metric (CHEM) that localizes hallucination-prone regions in image reconstruction models via multiscale representations and distribution-free conformal regression.
-
Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology
NTRM combines CNNs with tissue-level graph neural networks to model inter-tissue relationships, delivering 4.9% to 31.25% higher Dice scores than prior methods on a non-melanoma skin cancer histology segmentation benchmark.
-
SAMRI: Segment Any MRI
SAMRI fine-tunes only the mask decoder of SAM on 1.1 million MRI slices from 30 datasets to reach mean DSC 0.87 on 47 targets and strong zero-shot performance.
-
Category-based Galaxy Image Generation via Diffusion Models
GalCatDiff applies category embeddings and a novel Astro-RAB block inside diffusion models to produce galaxy images whose color and size distributions match observations more closely than prior generative approaches.
-
GroupKAN: Efficient Kolmogorov-Arnold Networks via Grouped Spline Modeling
GroupKAN reduces KAN parameter scaling via intra-group spline mappings, delivering 79.80% average IoU (+1.11% over U-KAN) at 47.6% of the parameters on BUSI, GlaS, and CVC datasets.
-
BGRem: A background noise remover for astronomical images based on a diffusion model
BGRem applies a supervised diffusion model to denoise MeerLICHT and Fermi-LAT images, raising true-positive source detections by roughly 7% when used before SExtractor.
-
A novel attention mechanism for noise-adaptive and robust segmentation of microtubules in microscopy images
ASE_Res_UNet with a novel noise-adaptive attention mechanism outperforms ablated variants and alternative architectures in segmenting microtubules from noisy synthetic and real microscopy images while using fewer parameters and transfers to other curvilinear structures.
-
MSLAU-Net: A Hybrid CNN-Transformer Network for Medical Image Segmentation
MSLAU-Net proposes a hybrid CNN-Transformer architecture using multi-scale linear attention and lightweight top-down aggregation that outperforms prior methods on medical segmentation benchmarks across three modalities.
-
Focal Modulation and Bidirectional Feature Fusion Network for Medical Image Segmentation
FM-BFF-Net combines focal modulation attention with bidirectional encoder-decoder fusion in a CNN-transformer architecture and reports higher Dice and Jaccard scores than recent methods across eight medical image datasets.
-
Clinical utility of foundation models in musculoskeletal MRI for biomarker fidelity and predictive outcomes
Fine-tuned foundation models produce reliable MSK MRI biomarkers that support workload-reducing triage and calibrated 48-month prediction of knee replacement and incident OA.