paper-with-me

홈 › Papers

Meta-Cal: Well-controlled Post-hoc Calibration by Ranking

2021-05-10 · Xingchen Ma, Matthew B. Blaschko

In many applications, it is desirable that a classifier not only makes accurate predictions, but also outputs calibrated posterior probabilities. However, many existing classifiers, especially deep neural network classifiers, tend to be uncalibrated. Post-hoc calibration is a technique to recalibrate a model by learning a calibration map. Existing approaches mostly focus on constructing calibration maps with low calibration errors, however, this quality is inadequate for a calibrator being useful. In this paper, we introduce two constraints that are worth consideration in designing a calibration map for post-hoc calibration. Then we present Meta-Cal, which is built from a base calibrator and a ranking model. Under some mild assumptions, two high-probability bounds are given with respect to these constraints. Empirical results on CIFAR-10, CIFAR-100 and ImageNet and a range of popular network architectures show our proposed method significantly outperforms the current state of the art for post-hoc multi-class classification calibration.

📄 PDF Abstract BibTeX arXiv:2105.04290

Code (1)

maxc01/metacal 공식 구현 pytorch

Tasks

Multi-class Classification

Similar Papers 제목 키워드 기반

Obtaining Calibrated Probabilities with Personalized Ranking Models

2021-12-09 · Wonbin Kweon, SeongKu Kang, Hwanjo Yu

For personalized ranking models, the well-calibrated probability of an item being preferred by a user has great practical value. While existing work shows promising results in image classification, probability calibratio…

image-classificationImage Classification

When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs

2026-06-29 · Zhichao Yang, Caiqi Zhang, Ruihan Yang, Chengzu Li 외 arxiv

Calibration evaluates whether a model confidence aligns with its empirical accuracy. Existing studies often compare the calibration of different large language models using global calibration metrics such as Expected Cal…

Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration

2023-05-23 · Daniel Deutsch, George Foster, Markus Freitag

Kendall's tau is frequently used to meta-evaluate how well machine translation (MT) evaluation metrics score individual translations. Its focus on pairwise score comparisons is intuitive but raises the question of how ti…

Machine Translation

MLPlatt: Simple Calibration Framework for Ranking Models

2026-01-13 · Piotr Bajger, Roman Dusek, Krzysztof Galias, Paweł Młyniec 외 arxiv

Ranking models are extensively used in e-commerce for relevance estimation. These models often suffer from poor interpretability and no scale calibration, particularly when trained with typical ranking loss functions. Th…

Post-hoc Reward Calibration: A Case Study on Length Bias

2024-09-25 · Zeyu Huang, Zihan Qiu, Zili Wang, Edoardo M. Ponti 외

Reinforcement Learning from Human Feedback aligns the outputs of Large Language Models with human values and preferences. Central to this process is the reward model (RM), which translates human feedback into training si…