Confidence Calibration for Object Detection and Segmentation
Calibrated confidence estimates obtained from neural networks are crucial, particularly for safety-critical applications such as autonomous driving or medical image diagnosis. However, although the task of confidence calibration has been investigated on classification problems, thorough investigations on object detection and segmentation problems are still missing. Therefore, we focus on the investigation of confidence calibration for object detection and segmentation models in this chapter. We introduce the concept of multivariate confidence calibration that is an extension of well-known calibration methods to the task of object detection and segmentation. This allows for an extended confidence calibration that is also aware of additional features such as bounding box/pixel position, shape information, etc. Furthermore, we extend the expected calibration error (ECE) to measure miscalibration of object detection and segmentation models. We examine several network architectures on MS COCO as well as on Cityscapes and show that especially object detection as well as instance segmentation models are intrinsically miscalibrated given the introduced definition of calibration. Using our proposed calibration methods, we have been able to improve calibration so that it also has a positive impact on the quality of segmentation masks as well.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingInstance SegmentationObjectobject-detectionObject DetectionSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On Model Calibration for Long-Tailed Object Detection and Instance Segmentation
Vanilla models for object detection and instance segmentation suffer from the heavy bias toward detecting frequent objects in the long-tailed setting. Existing methods address this issue mostly during training, e.g., by …
Instance SegmentationLong-tailed Object Detectionobject-detectionObject Detection+2Multivariate Confidence Calibration for Object Detection
Unbiased confidence estimates of neural networks are crucial especially for safety-critical applications. Many methods have been developed to calibrate biased confidence estimates. Though there is a variety of methods fo…
Classifier calibrationObjectobject-detectionObject DetectionUncertainty Calibration and its Application to Object Detection
Image-based environment perception is an important component especially for driver assistance systems or autonomous driving. In this scope, modern neuronal networks are used to identify multiple objects as well as the ac…
Autonomous DrivingInstance SegmentationObjectobject-detection+4From Black-box to White-box: Examining Confidence Calibration under different Conditions
Confidence calibration is a major concern when applying artificial neural networks in safety-critical applications. Since most research in this area has focused on classification in the past, confidence calibration in th…
Objectobject-detectionObject DetectionBayesian Confidence Calibration for Epistemic Uncertainty Modelling
Modern neural networks have found to be miscalibrated in terms of confidence calibration, i.e., their predicted confidence scores do not reflect the observed accuracy or precision. Recent work has introduced methods for …
object-detectionObject DetectionVariational Inference