Methods › General › Confidence Calibration › CCAC

Confidence Calibration with an Auxiliary Class)

CCAC

2 papers tagged archive 2025-07-28

Introduced by Zhihui Shao et al. in Calibrating Deep Neural Network Classifiers on Out-of-Distribution Datasets

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Confidence Calibration with an Auxiliary Class, or CCAC, is a post-hoc confidence calibration method for DNN classifiers on OOD datasets. The key feature of CCAC is an auxiliary class in the calibration model which separates mis-classified samples from correctly classified ones, thus effectively mitigating the target DNN’s being confidently wrong. It also reduces the number of free parameters in CCAC to reduce free parameters and facilitate transfer to a new unseen dataset.

PaperSource

Papers archive 2025-07-28

2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

2 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Model Predictive Control1
Reinforcement Learning (RL)1

Usage over time archive 2025-07-28

Papers per year tagged with CCAC: 2020 to 2020, peak 2 2 0 2020: 2 papers 2020
Papers per year the archive tags with this method, by the paper's archive date (2 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Confidence Calibration

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections