arXiv (All)
open access
Rethinking Post-Hoc Calibration in Semantic Segmentation
Reliable confidence estimates are essential in semantic segmentation, yet modern models often remain miscalibrated. We investigate two overlooked issues in post-hoc calibration. First, adding a constant to all logits leaves softmax probabilities unchanged, but several standard calibrators depend on
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling#1118741
- Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes#987527
- Does Model Uncertainty Track Human Ambiguity? Evidence from Multi-Annotator Vision Benchmarks#1128774
- Open-World Semantic Segmentation with Sensitivity Modeling#821975
- Generative Verification: Rethinking the Uncertainty Signal for Active Learning of Object Detection#1034030
Record · ID 1052223
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive