Papers Classifier calibration
“Classifier calibration” 태그가 달린 논문 39편 · 필터 해제
Full-range Binary Classifier Calibration for Stable Model Updates in Production
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 calibrationSimpson's Paradox in Behavioral Curves: How Aggregation Distorts Parametric Models of User Dynamics
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 calibrationToward Optimal Sampling Rate Selection and Unbiased Classification for Precise Animal Activity Recognition
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 RecognitionImpact of domain adaptation in deep learning for medical image classifications
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 AdaptationClassifier Calibration at Scale: An Empirical Study of Model-Agnostic Post-Hoc Methods
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 ClassificationConformal Safety Monitoring for Flight Testing: A Case Study in Data-Driven Safety Learning
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 calibrationEnhancing Diffusion Model Guidance through Calibration and Regularization
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 calibrationRethinking Calibration for Early-Exit Neural Networks
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 calibrationDeep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking
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 DrivingSculpting Margin Penalty: Intra-Task Adapter Merging and Classifier Calibration for Few-Shot Class-Incremental Learning
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 calibrationPrePrompt: Predictive prompting for class incremental learning
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+2Long-tailed Medical Diagnosis with Relation-aware Representation Learning and Iterative Classifier Calibration
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+4FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning
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 LearningEnhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer
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+1Improved User Identification through Calibrated Monte-Carlo Dropout
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 IdentificationAccuracy-Preserving Calibration via Statistical Modeling on Probability Simplex
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 QuantificationDecoupling Decision-Making in Fraud Prevention through Classifier Calibration for Business Logic Action
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 DetectionClassifier Calibration with ROC-Regularized Isotonic Regression
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 calibrationregressionNo Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier
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 LearningExpeditious Saliency-guided Mix-up through Random Gradient Thresholding
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