Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detection

• URL: http://arxiv.org/abs/2012.12195v1
• Date: Fri, 18 Dec 2020 09:11:44 GMT
• Title: Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detection
• Authors: Di Feng, Zining Wang, Yiyang Zhou, Lars Rosenbaum, Fabian Timm, Klaus Dietmayer, Masayoshi Tomizuka, Wei Zhan
• Abstract summary: In this work, we infer the uncertainty in bounding box labels from LiDAR point clouds based on a generative model. Comprehensive experiments show that the proposed model reflects complex environmental noises in LiDAR perception and the label quality. We propose Jaccard IoU as a new evaluation metric that extends IoU by incorporating label uncertainty.
• Score: 26.008419879970365
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The availability of many real-world driving datasets is a key reason behind the recent progress of object detection algorithms in autonomous driving. However, there exist ambiguity or even failures in object labels due to error-prone annotation process or sensor observation noise. Current public object detection datasets only provide deterministic object labels without considering their inherent uncertainty, as does the common training process or evaluation metrics for object detectors. As a result, an in-depth evaluation among different object detection methods remains challenging, and the training process of object detectors is sub-optimal, especially in probabilistic object detection. In this work, we infer the uncertainty in bounding box labels from LiDAR point clouds based on a generative model, and define a new representation of the probabilistic bounding box through a spatial uncertainty distribution. Comprehensive experiments show that the proposed model reflects complex environmental noises in LiDAR perception and the label quality. Furthermore, we propose Jaccard IoU (JIoU) as a new evaluation metric that extends IoU by incorporating label uncertainty. We conduct an in-depth comparison among several LiDAR-based object detectors using the JIoU metric. Finally, we incorporate the proposed label uncertainty in a loss function to train a probabilistic object detector and to improve its detection accuracy. We verify our proposed methods on two public datasets (KITTI, Waymo), as well as on simulation data. Code is released at https://bit.ly/2W534yo.

Related papers

• Bayesian Detector Combination for Object Detection with Crowdsourced Annotations [49.43709660948812]
  Acquiring fine-grained object detection annotations in unconstrained images is time-consuming, expensive, and prone to noise. We propose a novel Bayesian Detector Combination (BDC) framework to more effectively train object detectors with noisy crowdsourced annotations. BDC is model-agnostic, requires no prior knowledge of the annotators' skill level, and seamlessly integrates with existing object detection models.
  arXiv  Detail & Related papers  (2024-07-10T18:00:54Z)
• Credible Teacher for Semi-Supervised Object Detection in Open Scene [106.25850299007674]
  In Open Scene Semi-Supervised Object Detection (O-SSOD), unlabeled data may contain unknown objects not observed in the labeled data. It is detrimental to the current methods that mainly rely on self-training, as more uncertainty leads to the lower localization and classification precision of pseudo labels. We propose Credible Teacher, an end-to-end framework to prevent uncertain pseudo labels from misleading the model.
  arXiv  Detail & Related papers  (2024-01-01T08:19:21Z)
• SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving [160.57870373052577]
  We propose a saliency-based OD algorithm (SalienDet) to detect unknown objects. Our SalienDet utilizes a saliency-based algorithm to enhance image features for object proposal generation. We design a dataset relabeling approach to differentiate the unknown objects from all objects in training sample set to achieve Open-World Detection.
  arXiv  Detail & Related papers  (2023-05-11T16:19:44Z)
• Robust Object Detection With Inaccurate Bounding Boxes [27.664730859319707]
  Learning accurate object detectors often requires large-scale training data with precise object bounding boxes. In this work, we aim to address the challenge of learning robust object detectors with inaccurate bounding boxes. By treating an object as a bag of instances, we introduce an Object-Aware Multiple Instance Learning approach.
  arXiv  Detail & Related papers  (2022-07-20T06:57:30Z)
• GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation [70.75100533512021]
  In this paper, we formulate the label uncertainty problem as the diversity of potentially plausible bounding boxes of objects. We propose GLENet, a generative framework adapted from conditional variational autoencoders, to model the one-to-many relationship between a typical 3D object and its potential ground-truth bounding boxes with latent variables. The label uncertainty generated by GLENet is a plug-and-play module and can be conveniently integrated into existing deep 3D detectors.
  arXiv  Detail & Related papers  (2022-07-06T06:26:17Z)
• Object Detection as Probabilistic Set Prediction [3.7599363231894176]
  We present a proper scoring rule for evaluating and training probabilistic object detectors. Our results indicate that the training of existing detectors is optimized toward non-probabilistic metrics.
  arXiv  Detail & Related papers  (2022-03-15T15:13:52Z)
• CertainNet: Sampling-free Uncertainty Estimation for Object Detection [65.28989536741658]
  Estimating the uncertainty of a neural network plays a fundamental role in safety-critical settings. In this work, we propose a novel sampling-free uncertainty estimation method for object detection. We call it CertainNet, and it is the first to provide separate uncertainties for each output signal: objectness, class, location and size.
  arXiv  Detail & Related papers  (2021-10-04T17:59:31Z)
• Incorporating Data Uncertainty in Object Tracking Algorithms [2.3204178451683264]
  Object tracking methods rely on measurement error models, typically in the form of measurement noise, false positive rates, and missed detection rates. For detections generated from neural-network processed camera inputs, measurement error statistics are not sufficient to represent the primary source of errors. We investigate incorporating data uncertainty into object tracking methods such as to improve the ability to track objects, and particularly those which out-of-distribution w.r.t. training data.
  arXiv  Detail & Related papers  (2021-09-22T05:30:46Z)
• Inferring Spatial Uncertainty in Object Detection [35.28872968233385]
  We propose a generative model to estimate bounding box label uncertainties from LiDAR point clouds. Comprehensive experiments show that the proposed model represents uncertainties commonly seen in driving scenarios. We propose an extension of IoU, called the Jaccard IoU (JIoU), as a new evaluation metric that incorporates label uncertainty.
  arXiv  Detail & Related papers  (2020-03-07T19:29:43Z)
• Object Detection as a Positive-Unlabeled Problem [78.2955013126312]
  We propose treating object detection as a positive-unlabeled (PU) problem, which removes the assumption that unlabeled regions must be negative. We demonstrate that our proposed PU classification loss outperforms the standard PN loss on PASCAL VOC and MS COCO across a range of label missingness, as well as on Visual Genome and DeepLesion with full labels.
  arXiv  Detail & Related papers  (2020-02-11T20:49:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.