Calibration Attention: Learning Reliability-Aware Representations for Vision Transformers
Most calibration methods operate at the logit level, implicitly assuming that miscalibration can be corrected without changing the underlying representation. We challenge this assumption and propose \textbf{Calibration Attention (CalAttn)}, a \emph{representation-aware} calibration module for vision transformers that couples instance-wise temperature scaling to transformer token geometry under a proper scoring objective. CalAttn predicts a sample-specific temperature from the \texttt{[CLS]} token and backpropagates calibration gradients into the backbone, thereby reshaping the uncertainty structure of the representation rather than post-hoc adjusting confidence. This yields \emph{token-conditioned uncertainty modulation} with negligible overhead (\(<0.1\%\) additional parameters). Across multiple datasets with ViT/DeiT/Swin backbones, CalAttn consistently improves calibration while preserving accuracy, achieving relative ECE reductions of \(3.7\%\) to \(77.7\%\) over strong baselines across diverse training objectives. Our results indicate that treating calibration as a representation-level problem is a practical and effective direction for trustworthy uncertainty estimation in transformers. Code: https://github.com/EagleAdelaide/CalibrationAttention-CalAttn-
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
RABC-Net: Reliability-Aware Annotation-Free Skin Lesion Segmentation for Low-Resource Dermoscopy
Pixel-level annotation is costly in low-resource dermoscopy. We present RABC-Net, a reliability-aware annotation-free segmentation system that combines pseudo-label reliability learning, restricted target-domain adaptati…
Skin Lesion SegmentationDomain AdaptationUncertainty-Aware Online Extrinsic Calibration: A Conformal Prediction Approach
Accurate sensor calibration is crucial for autonomous systems, yet its uncertainty quantification remains underexplored. We present the first approach to integrate uncertainty awareness into online extrinsic calibration,…
Conformal PredictionPredictionPrediction IntervalsSensor Fusion+1Concerning Uncertainty -- A Systematic Survey of Uncertainty-Aware XAI
This paper surveys uncertainty-aware explainable artificial intelligence (UAXAI), examining how uncertainty is incorporated into explanatory pipelines and how such methods are evaluated. Across the literature, three recu…
FVG-PT: Adaptive Foreground View-Guided Prompt Tuning for Vision-Language Models
CLIP-based prompt tuning enables pretrained Vision-Language Models (VLMs) to efficiently adapt to downstream tasks. Although existing studies have made significant progress, they pay limited attention to changes in the i…
Decision-Aware Uncertainty Evaluation of Vision-Language Model-Based Early Action Anticipation for Human-Robot Interaction
Robots in shared workspaces must interpret human actions from partial, ambiguous observations, where overconfident early predictions can lead to unsafe or disruptive interaction. This challenge is amplified in egocentric…
Action AnticipationAction Recognition