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.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
Prototype-conditioned Mixture-of-Experts synthesizes missing modalities in federated learning and beats prior methods on heterogeneous chest X-ray clients without public data.
LPID confines perturbations to the face region and optimizes them through a differentiable crop-and-resize model, holding attacker accuracy below 10% on unseen identities where prior unlearnable-example methods collapse to 37–74%.
A new person re-identification benchmark combines visible-infrared and clothing-change settings, and a progressive disentangle-then-align network is reported as the new state of the art on it.
Keypoint detection plus graph grouping produces per-cell bounding boxes for instance segmentation, outperforming prior methods on two cell datasets.
AC3S adds a self-supervised visual prompt modulator to ControlNet diffusion and a multi-agent VLM prompt composer to generate photorealistic images with accurate 2D/3D annotations while avoiding over-conditioning.
cGAN data augmentation with feature-based filtering improves ResNet18 CIN grading accuracy from 66.3% to 71.7% on segmented epithelium patches.
citing papers explorer
-
XAttnRes: Cross-Stage Attention Residuals for Medical Image Segmentation
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.
-
ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
Prototype-conditioned Mixture-of-Experts synthesizes missing modalities in federated learning and beats prior methods on heterogeneous chest X-ray clients without public data.
-
Unlearnable Faces: Privacy Protection Surviving Extraction Pipeline
LPID confines perturbations to the face region and optimizes them through a differentiable crop-and-resize model, holding attacker accuracy below 10% on unseen identities where prior unlearnable-example methods collapse to 37–74%.
-
CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification
A new person re-identification benchmark combines visible-infrared and clothing-change settings, and a progressive disentangle-then-align network is reported as the new state of the art on it.
-
Multi-scale Cell Instance Segmentation with Keypoint Graph based Bounding Boxes
Keypoint detection plus graph grouping produces per-cell bounding boxes for instance segmentation, outperforming prior methods on two cell datasets.
-
AC3S: Adaptive Conditioning for 3D-Aware Synthetic Data Generation
AC3S adds a self-supervised visual prompt modulator to ControlNet diffusion and a multi-agent VLM prompt composer to generate photorealistic images with accurate 2D/3D annotations while avoiding over-conditioning.
-
Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classification
cGAN data augmentation with feature-based filtering improves ResNet18 CIN grading accuracy from 66.3% to 71.7% on segmented epithelium patches.