发表机构
Chung-Ang University（中央大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有检测校准仅关注框级定位的不足，提出ReDC框架，定义坐标级对齐与偏差方向，生成可靠坐标级置信度，实验表明其定位精度优于现有方法且覆盖原有校准方法范围。
AI 中文摘要
基于深度学习的目标检测器除了具备有竞争力的检测性能外，还需要具备可信度，但深度神经网络往往容易出现过度自信的预测，将高置信度分数分配给可能不准确的预测。为了提高置信度分数与预测准确性之间的一致性，现有方法基于框级定位来校准置信度，例如精度或与真实边界框的交并比。然而，框级定位仅反映了预测框与真实框之间的一致性程度，导致用于框级准确性的校准置信度分数无法捕捉框坐标的定位准确性。为解决该问题，我们提出了一种新颖的事后校准框架ReDC（重新思考检测校准），该框架提供可靠的坐标级置信度分数，包括方向信息。该框架定义了预测与真实之间的坐标级对齐和偏差方向，基于对齐度量的置信度重新编码生成可靠的坐标级置信度分数，而方向位移估计则预测坐标级偏差方向。在域内和域外场景下的大量实验表明，与现有方法相比，所提方法能更精确地表达检测对象的坐标级定位，此外，我们的方法通过将坐标级置信度分数聚合为框级定位，覆盖了现有校准方法的表示范围。
英文摘要
Deep learning based object detectors require trustworthiness beyond competitive detection performance, but deep neural networks are prone to overconfident predictions, assigning high confidence scores to predictions that are likely to be inaccurate. To improve the alignment between confidence scores and prediction accuracy, existing methods calibrate confidence scores based on box-level localization, such as precision or intersection over union with the ground truth bounding box. However, box-level localization reflects only a measure of agreement between the predicted box and the ground truth, resulting in calibrated confidence scores for box-level accuracy failing to capture the localization accuracy of coordinates of box. To tackle this issue, we propose a novel post-hoc calibration framework, rethinking detection calibration (ReDC), which provides reliable coordinate-level confidence scores, including directional information. The proposed framework defines coordinate-wise alignment and deviation direction between predictions and ground truth. Based on the alignment measure, confidence re-encoding produces reliable coordinate-level confidence scores, while directional displacement estimation predicts coordinate-wise deviation directions. Extensive experiments under in-domain and out-domain scenarios demonstrate that the proposed approach expresses the coordinate-wise localization of detected objects more precisely than existing methods. Furthermore, our method covers the representational scope of prior calibration approaches by aggregating coordinate-level confidence scores into box-level localization.
CommentsAccepted by ECCV 2026
