paper-with-me

Papers Classifier calibration

“Classifier calibration” 태그가 달린 논문 39편 · 필터 해제

Full-range Binary Classifier Calibration for Stable Model Updates in Production

2026-07-06 · Konstantin Berlin arxiv

Detection models running in adversarial environments face a malicious distribution that drifts rapidly while the benign distribution stays comparatively stable, so teams retrain and redeploy constantly to stay ahead of n…

Classifier calibration

Simpson's Paradox in Behavioral Curves: How Aggregation Distorts Parametric Models of User Dynamics

2026-05-10 · Chao Zhou arxiv

Behavioral curve modeling -- fitting parametric functions to engagement-versus-exposure data -- is standard practice in recommendation, advertising, and clinical dosing. We show that aggregation introduces a systematic d…

Classifier calibration

Toward Optimal Sampling Rate Selection and Unbiased Classification for Precise Animal Activity Recognition

2026-04-01 · Axiu Mao, Meilu Zhu, Lei Shen, Xiaoshuai Wang 외 arxiv

With the rapid advancements in deep learning techniques, wearable sensor-aided animal activity recognition (AAR) has demonstrated promising performance, thereby improving livestock management efficiency as well as animal…

Classifier calibrationActivity Recognition

Impact of domain adaptation in deep learning for medical image classifications

2026-02-10 · Yihang Wu, Ahmad Chaddad arxiv

Domain adaptation (DA) is a quickly expanding area in machine learning that involves adjusting a model trained in one domain to perform well in another domain. While there have been notable progressions, the fundamental …

Skin Cancer ClassificationClassifier calibrationFederated LearningDomain Adaptation

Classifier Calibration at Scale: An Empirical Study of Model-Agnostic Post-Hoc Methods

2026-01-19 · Valery Manokhin, Daniel Grønhaug arxiv

We study model-agnostic post-hoc calibration methods intended to improve probabilistic predictions in supervised binary classification on real i.i.d. tabular data, with particular emphasis on conformal and Venn-based app…

Classifier calibrationBinary Classification

Conformal Safety Monitoring for Flight Testing: A Case Study in Data-Driven Safety Learning

2025-11-25 · Aaron O. Feldman, D. Isaiah Harp, Joseph Duncan, Mac Schwager arxiv

We develop a data-driven approach for runtime safety monitoring in flight testing, where pilots perform maneuvers on aircraft with uncertain parameters. Because safety violations can arise unexpectedly as a result of the…

Classifier calibration

Enhancing Diffusion Model Guidance through Calibration and Regularization

2025-11-08 · Seyed Alireza Javid, Amirhossein Bagheri, Nuria González-Prelcic arxiv

Classifier-guided diffusion models have emerged as a powerful approach for conditional image generation, but they suffer from overconfident predictions during early denoising steps, causing the guidance gradient to vanis…

Conditional Image GenerationClassifier calibration

Rethinking Calibration for Early-Exit Neural Networks

2025-08-29 · Piotr Kubaty, Filip Szatkowski, Grzegorz Choczyński, Eric Nalisnick 외 arxiv

Early-exit neural networks (EENNs) accelerate inference by allowing intermediate classifiers to stop computation once predictions are confident enough. Most methods rely on confidence thresholds for exiting, and conseque…

Classifier calibration

Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking

2025-08-12 · Jiani Ni, He Zhao, Yibo Yang, Dandan Guo arxiv

In recent years, deep neural networks (DNNs) have shown competitive results in many fields. Despite this success, they often suffer from poor calibration, especially in safety-critical scenarios such as autonomous drivin…

Classifier calibrationAutonomous Driving

Sculpting Margin Penalty: Intra-Task Adapter Merging and Classifier Calibration for Few-Shot Class-Incremental Learning

2025-08-07 · Liang Bai, Hong Song, Jinfu Li, Yucong Lin 외 arxiv

Real-world applications often face data privacy constraints and high acquisition costs, making the assumption of sufficient training data in incremental tasks unrealistic and leading to significant performance degradatio…

Few-Shot Class-Incremental Learningparameter-efficient fine-tuningClassifier calibration

PrePrompt: Predictive prompting for class incremental learning

2025-05-13 · Libo Huang, Zhulin An, Chuanguang Yang, Boyu Diao 외

Class Incremental Learning (CIL) based on pre-trained models offers a promising direction for open-world continual learning. Existing methods typically rely on correlation-based strategies, where an image's classificatio…

Classifier calibrationclass-incremental learningClass Incremental LearningContinual Learning+2

Long-tailed Medical Diagnosis with Relation-aware Representation Learning and Iterative Classifier Calibration

2025-02-05 · Li Pan, Yupei Zhang, Qiushi Yang, Tan Li 외

Recently computer-aided diagnosis has demonstrated promising performance, effectively alleviating the workload of clinicians. However, the inherent sample imbalance among different diseases leads algorithms biased to the…

Classifier calibrationDiagnosticimage-classificationImage Classification+4

FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning

2025-01-09 · Yanbing Zhou, Xiangmou Qu, Chenlong You, Jiyang Zhou 외

Prototype-based federated learning has emerged as a promising approach that shares lightweight prototypes to transfer knowledge among clients with data heterogeneity in a model-agnostic manner. However, existing methods …

Classifier calibrationContrastive LearningFederated LearningRepresentation Learning

Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer

2024-12-20 · Xinyue Chen, Miaojing Shi, Zijian Zhou, Lianghua He 외

Generalized few-shot semantic segmentation (GFSS) aims to segment objects of both base and novel classes, using sufficient samples of base classes and few samples of novel classes. Representative GFSS approaches typicall…

Classifier calibrationFew-Shot Semantic SegmentationGeneralized Few-Shot Semantic SegmentationSemantic Segmentation+1

Improved User Identification through Calibrated Monte-Carlo Dropout

2024-09-29 · Knowledge-Based Systems 2024 9 · Rouhollah Ahmadian, Mehdi Ghatee, Johan Wahlström

This paper presents an enhanced approach to user identification using smartphone and wearable sensor data. Our methodology involves segmenting input data and independently analyzing subsequences with CNNs. During testing…

Classifier calibrationUncertainty QuantificationUser Identification

Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex

2024-02-21 · Yasushi Esaki, Akihiro Nakamura, Keisuke Kawano, Ryoko Tokuhisa 외

Classification models based on deep neural networks (DNNs) must be calibrated to measure the reliability of predictions. Some recent calibration methods have employed a probabilistic model on the probability simplex. How…

Classifier calibrationUncertainty Quantification

Decoupling Decision-Making in Fraud Prevention through Classifier Calibration for Business Logic Action

2024-01-10 · Emanuele Luzio, Moacir Antonelli Ponti, Christian Ramirez Arevalo, Luis Argerich

Machine learning models typically focus on specific targets like creating classifiers, often based on known population feature distributions in a business context. However, models calculating individual features adapt ov…

Classifier calibrationDecision MakingFraud Detection

Classifier Calibration with ROC-Regularized Isotonic Regression

2023-11-21 · Eugene Berta, Francis Bach, Michael Jordan

Calibration of machine learning classifiers is necessary to obtain reliable and interpretable predictions, bridging the gap between model confidence and actual probabilities. One prominent technique, isotonic regression …

Classifier calibrationregression

No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier

2023-03-17 · ICCV 2023 1 · Zexi Li, Xinyi Shang, Rui He, Tao Lin 외

Data heterogeneity is an inherent challenge that hinders the performance of federated learning (FL). Recent studies have identified the biased classifiers of local models as the key bottleneck. Previous attempts have use…

Classifier calibrationFederated Learning

Expeditious Saliency-guided Mix-up through Random Gradient Thresholding

2022-12-09 · Minh-Long Luu, Zeyi Huang, Eric P. Xing, Yong Jae Lee 외

Mix-up training approaches have proven to be effective in improving the generalization ability of Deep Neural Networks. Over the years, the research community expands mix-up methods into two directions, with extensive ef…

Classifier calibrationImage ClassificationObject LocalizationWeakly-Supervised Object Localization
1–20 / 39 다음 →