Introduces the ASTAD task and training-free ASTModel framework for semantically consistent asymmetric style transfer using labeled synthetic content and unlabeled real references.
Advances in neural information processing systems34, 12077–12090 (2021)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
WaterGen decouples scene generation from medium degradation in a two-stage latent diffusion process to produce controllable realistic underwater images that improve downstream restoration and segmentation.
GroundingAnomaly uses a Spatial Conditioning Module and Gated Self-Attention in a frozen diffusion U-Net to synthesize spatially accurate few-shot anomalies, reaching SOTA on MVTec AD and VisA for detection, segmentation, and instance detection.
STARQ uses a SegFormer-based multi-scale transformer with Gaussian-kernel pseudo-label propagation from sparse OpenAQ stations to downscale CAMS PM2.5 forecasts from 0.4° to 0.01° (~1 km) across Europe, achieving MAE 5.87 and R² 0.24 on held-out stations.
WoundFormer modifies SegFormer with a spatially-preserving multi-scale aggregation head for multi-class wound tissue segmentation, reporting 81.9% Dice on the WoundTissueSeg dataset with gains over baselines.
DepthPolyp is a compact model using pseudo-depth multi-task learning and efficient feature modules that delivers strong generalization and real-time performance for polyp segmentation in noisy colonoscopy data.
citing papers explorer
-
ASTAD: Asymmetric Style Transfer for Synthetic-to-Real Adaptation in Autonomous Driving
Introduces the ASTAD task and training-free ASTModel framework for semantically consistent asymmetric style transfer using labeled synthetic content and unlabeled real references.
-
WaterGen: Decoupling Scene and Medium in Underwater Image Generation
WaterGen decouples scene generation from medium degradation in a two-stage latent diffusion process to produce controllable realistic underwater images that improve downstream restoration and segmentation.
-
GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis
GroundingAnomaly uses a Spatial Conditioning Module and Gated Self-Attention in a frozen diffusion U-Net to synthesize spatially accurate few-shot anomalies, reaching SOTA on MVTec AD and VisA for detection, segmentation, and instance detection.
-
Air Quality Downscaling with Station-Guided Pseudo-Supervision
STARQ uses a SegFormer-based multi-scale transformer with Gaussian-kernel pseudo-label propagation from sparse OpenAQ stations to downscale CAMS PM2.5 forecasts from 0.4° to 0.01° (~1 km) across Europe, achieving MAE 5.87 and R² 0.24 on held-out stations.
-
WoundFormer: Multi-Scale Spatial Feature Fusion for Multi-Class Wound Tissue Segmentation
WoundFormer modifies SegFormer with a spatially-preserving multi-scale aggregation head for multi-class wound tissue segmentation, reporting 81.9% Dice on the WoundTissueSeg dataset with gains over baselines.
-
DepthPolyp: Pseudo-Depth Guided Lightweight Segmentation for Real-Time Colonoscopy
DepthPolyp is a compact model using pseudo-depth multi-task learning and efficient feature modules that delivers strong generalization and real-time performance for polyp segmentation in noisy colonoscopy data.