The paper defines four matching strategies for panoptic quality via degree-bounded bipartite assignment and introduces vertex-based TP/FN/FP counting that extends to part-aware evaluation.
arXiv preprint arXiv:2504.12527 (2025)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4verdicts
UNVERDICTED 4representative citing papers
Multi-class blob and CC losses via one-vs-rest decomposition and per-component weighting improve foreground Dice, rare-class Dice, and Panoptic Quality on BraTS-METS 2025 compared to baseline.
Contrast-X benchmark and FlowMI model enable synthesis of contrast-enhanced images from arbitrary non-contrast modality inputs using multi-modal flow matching.
Ensembling inpainting models with median filtering, histogram matching, pixel averaging, and lightweight U-Net refinement yields more anatomically plausible and accurate inpainted MRI regions than individual baseline models.
citing papers explorer
-
Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation
The paper defines four matching strategies for panoptic quality via degree-bounded bipartite assignment and introduces vertex-based TP/FN/FP counting that extends to part-aware evaluation.
-
Instance Awareness of Multi-class Semantic Segmentation Loss Functions
Multi-class blob and CC losses via one-vs-rest decomposition and per-component weighting improve foreground Dice, rare-class Dice, and Panoptic Quality on BraTS-METS 2025 compared to baseline.
-
Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching
Contrast-X benchmark and FlowMI model enable synthesis of contrast-enhanced images from arbitrary non-contrast modality inputs using multi-modal flow matching.
-
Post-Processing Methods for Improving Accuracy in MRI Inpainting
Ensembling inpainting models with median filtering, histogram matching, pixel averaging, and lightweight U-Net refinement yields more anatomically plausible and accurate inpainted MRI regions than individual baseline models.