paper-with-me

Papers

Confidence Calibration for Object Detection and Segmentation

2022-02-25 · Fabian Küppers, Anselm Haselhoff, Jan Kronenberger, Jonas Schneider

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.

📄 PDF Abstract BibTeX arXiv:2202.12785

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingInstance SegmentationObjectobject-detectionObject DetectionSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

2021-07-05 · NeurIPS 2021 12 · Tai-Yu Pan, Cheng Zhang, Yandong Li, Hexiang Hu 외

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+2

Multivariate Confidence Calibration for Object Detection

2020-04-28 · Fabian Küppers, Jan Kronenberger, Amirhossein Shantia, Anselm Haselhoff

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 Detection

Uncertainty Calibration and its Application to Object Detection

2023-02-06 · Fabian Küppers

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+4

From Black-box to White-box: Examining Confidence Calibration under different Conditions

2021-01-08 · Franziska Schwaiger, Maximilian Henne, Fabian Küppers, Felippe Schmoeller Roza 외

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 Detection

Bayesian Confidence Calibration for Epistemic Uncertainty Modelling

2021-09-21 · Fabian Küppers, Jan Kronenberger, Jonas Schneider, Anselm Haselhoff

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