Research map / Label-efficient and robust learning / Noisy labels
On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Optimize Accuracy instead of Dice | Segmentation under noisy labels · General marginal function | optimal segmentation volume | Mixed |
| Constrain feasible segmentations to the expected target volume | Accuracy and Dice optimization · Fixed-volume segmentations | optimal segmentation | No clear effect |
| Optimize Accuracy or Dice with noisy marginal labels without a volume constraint | Optimal segmentation · Gold Atlas and LIDC-IDRI | volume relative to expected target volume: 0.778; 1.267; 1.002; 1.432 | Mixed |
Closest papers by meaning
- The Impact Label Noise and Choice of Threshold has on Cross-Entropy and Soft-Dice in Image Segmentation (CVPR 2025 · similarity 0.88)
- Learning to Segment from Noisy Annotations: A Spatial Correction Approach (ICLR 2023 · similarity 0.87)
- Every Component Counts: Rethinking the Measure of Success for Medical Semantic Segmentation in Multi-Instance Segmentation Tasks (AAAI 2025 · similarity 0.85)
- Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline (CVPR 2025 · similarity 0.85)
- S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging (AAAI 2025 · similarity 0.84)
- Uncertainty-aware Fine-tuning of Segmentation Foundation Models (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.