Deep 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 driving and healthcare, where unreliable confidence estimates can lead to serious consequences. Recent studies have focused on improving calibration by modifying the classifier, yet such efforts remain limited. Moreover, most existing approaches overlook calibration errors caused by underconfidence, which can be equally detrimental. To address these challenges, we propose MaC-Cal, a novel mask-based classifier calibration method that leverages stochastic sparsity to enhance the alignment between confidence and accuracy. MaC-Cal adopts a two-stage training scheme with adaptive sparsity, dynamically adjusting mask retention rates based on the deviation between confidence and accuracy. Extensive experiments show that MaC-Cal achieves superior calibration performance and robustness under data corruption, offering a practical and effective solution for reliable confidence estimation in DNNs.
Code (0)
등록된 구현이 없습니다.
Tasks
Classifier calibrationAutonomous DrivingSimilar Papers 제목 키워드 기반
Adapting to Label Shift with Bias-Corrected Calibration
Label shift refers to the phenomenon where the marginal probability p(y) of observing a particular class changes between the training and test distributions, while the conditional probability p(x|y) stays fixed. This is …
Diabetic Retinopathy DetectionDomain Adaptationimage-classificationImage Classification+1Bayesian Sparse Low-Rank Adaptation for Large Language Model Uncertainty Estimation
Large language models (LLMs) exhibit remarkable reasoning capabilities, but their task-specific fine-tuning is notoriously plagued by overconfidence, severely hindering trustworthy deployment. We propose Data-Adaptive Lo…
Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning
Exemplar-Free Class-Incremental Learning (EFCIL) aims to sequentially learn from distinct categories without retaining exemplars but easily suffers from catastrophic forgetting of learned knowledge. While existing EFCIL …
class-incremental learningClass Incremental LearningExemplar-FreeIncremental Learning+1Recalibrating binary probabilistic classifiers
Recalibration of binary probabilistic classifiers to a target prior probability is an important task in areas like credit risk management. We analyse methods for recalibration from a distribution shift perspective. Distr…
ManagementUnsupervised Calibration under Covariate Shift
A probabilistic model is said to be calibrated if its predicted probabilities match the corresponding empirical frequencies. Calibration is important for uncertainty quantification and decision making in safety-critical …
Decision MakingDomain AdaptationUncertainty Quantification