A feature-space method that erases usable identity information from face images via learnable perturbations and a Face Revive Generator, rendering them ineffective for deepfake swapping while preserving visual quality.
Swin-unet: Unet-like pure transformer for medical image segmentation
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
MedFlowSeg is a conditional flow matching model for medical image segmentation that adds dual-branch spatial attention and frequency-aware attention to achieve more efficient inference than diffusion models while improving structural consistency.
Label dropout mitigates shortcut learning in multi-dataset partially labelled echocardiography segmentation, improving Dice scores by 62% and 25% on two cardiac structures.
2D diffusion-generated synthetic X-rays enable training of anatomical landmark detectors that generalize to real images with performance rivaling real-data training.
Attention-ResUNet reaches 99.30% mean Dice score on the HC18 fetal head ultrasound dataset, outperforming ResUNet, Attention U-Net, Swin U-Net, U-Net, and U-Net++ with statistical significance.
Convolutional models like YOLOv11 and Mask R-CNN outperform transformer-based models for tree canopy segmentation when fine-tuned on just 150 images.
citing papers explorer
-
ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation
A feature-space method that erases usable identity information from face images via learnable perturbations and a Face Revive Generator, rendering them ineffective for deepfake swapping while preserving visual quality.
-
MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention
MedFlowSeg is a conditional flow matching model for medical image segmentation that adds dual-branch spatial attention and frequency-aware attention to achieve more efficient inference than diffusion models while improving structural consistency.
-
Label Dropout: Improved Deep Learning Echocardiography Segmentation Using Multiple Datasets With Domain Shift and Partial Labelling
Label dropout mitigates shortcut learning in multi-dataset partially labelled echocardiography segmentation, improving Dice scores by 62% and 25% on two cardiac structures.
-
2D Versus 3D Diffusion for In Silico Training of Interventional X-ray AI Models
2D diffusion-generated synthetic X-rays enable training of anatomical landmark detectors that generalize to real images with performance rivaling real-data training.
-
Attention-ResUNet for Automated Fetal Head Segmentation
Attention-ResUNet reaches 99.30% mean Dice score on the HC18 fetal head ultrasound dataset, outperforming ResUNet, Attention U-Net, Swin U-Net, U-Net, and U-Net++ with statistical significance.
-
Sparse Data Tree Canopy Segmentation: Fine-Tuning Leading Pretrained Models on Only 150 Images
Convolutional models like YOLOv11 and Mask R-CNN outperform transformer-based models for tree canopy segmentation when fine-tuned on just 150 images.