Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentation

• URL: http://arxiv.org/abs/2404.11266v1
• Date: Wed, 17 Apr 2024 11:17:12 GMT
• Title: Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentation
• Authors: Florian Heidecker, Ahmad El-Khateeb, Maarten Bieshaar, Bernhard Sick,
• Abstract summary: We present corner case criteria based on the predictive uncertainty. We evaluate each corner case criterion using the COCO and the NuImages dataset. We also provide a corner case decision function that allows us to distinguish each object into True Positive (TP), localization and/or classification corner case, or False Positive (FP)
• Score: 2.9419365092937086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The operating environment of a highly automated vehicle is subject to change, e.g., weather, illumination, or the scenario containing different objects and other participants in which the highly automated vehicle has to navigate its passengers safely. These situations must be considered when developing and validating highly automated driving functions. This already poses a problem for training and evaluating deep learning models because without the costly labeling of thousands of recordings, not knowing whether the data contains relevant, interesting data for further model training, it is a guess under which conditions and situations the model performs poorly. For this purpose, we present corner case criteria based on the predictive uncertainty. With our corner case criteria, we are able to detect uncertainty-based corner cases of an object instance segmentation model without relying on ground truth (GT) data. We evaluated each corner case criterion using the COCO and the NuImages dataset to analyze the potential of our approach. We also provide a corner case decision function that allows us to distinguish each object into True Positive (TP), localization and/or classification corner case, or False Positive (FP). We also present our first results of an iterative training cycle that outperforms the baseline and where the data added to the training dataset is selected based on the corner case decision function.

Related papers

• 3CSim: CARLA Corner Case Simulation for Control Assessment in Autonomous Driving [0.44938884406455726]
  This framework is designed to address the limitations of traditional AD model training by focusing on non-standard, rare, and cognitively challenging scenarios. Our approach introduces a taxonomy of corner cases categorized into state anomalies, behavior anomalies, and evidence-based anomalies. We implement 32 unique corner cases with adjustable parameters, including 9 predefined weather conditions, timing, and traffic density.
  arXiv  Detail & Related papers  (2024-08-30T12:38:22Z)
• SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation [55.87169702896249]
  Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift. We propose a framework to evaluate DA methods and present a fair evaluation of existing shallow algorithms, including reweighting, mapping, and subspace alignment. Our benchmark highlights the importance of realistic validation and provides practical guidance for real-life applications.
  arXiv  Detail & Related papers  (2024-07-16T12:52:29Z)
• Placing Objects in Context via Inpainting for Out-of-distribution Segmentation [59.00092709848619]
  Placing Objects in Context (POC) is a pipeline to realistically add objects to an image. POC can be used to extend any dataset with an arbitrary number of objects. We present different anomaly segmentation datasets based on POC-generated data and show that POC can improve the performance of recent state-of-the-art anomaly fine-tuning methods.
  arXiv  Detail & Related papers  (2024-02-26T08:32:41Z)
• CC-SGG: Corner Case Scenario Generation using Learned Scene Graphs [6.131026007721575]
  Corner case scenarios are an essential tool for testing and validating the safety of autonomous vehicles (AVs) We introduce a novel approach based on Heterogeneous Graph Neural Networks (HGNNs) to transform regular driving scenarios into corner cases. Our model successfully learned to produce corner cases from input scene graphs, achieving 89.9% prediction accuracy on our testing dataset.
  arXiv  Detail & Related papers  (2023-09-18T14:59:11Z)
• Explaining Cross-Domain Recognition with Interpretable Deep Classifier [100.63114424262234]
  Interpretable Deep (IDC) learns the nearest source samples of a target sample as evidence upon which the classifier makes the decision. Our IDC leads to a more explainable model with almost no accuracy degradation and effectively calibrates classification for optimum reject options.
  arXiv  Detail & Related papers  (2022-11-15T15:58:56Z)
• Data-SUITE: Data-centric identification of in-distribution incongruous examples [81.21462458089142]
  Data-SUITE is a data-centric framework to identify incongruous regions of in-distribution (ID) data. We empirically validate Data-SUITE's performance and coverage guarantees.
  arXiv  Detail & Related papers  (2022-02-17T18:58:31Z)
• Just Label What You Need: Fine-Grained Active Selection for Perception and Prediction through Partially Labeled Scenes [78.23907801786827]
  We introduce generalizations that ensure that our approach is both cost-aware and allows for fine-grained selection of examples through partially labeled scenes. Our experiments on a real-world, large-scale self-driving dataset suggest that fine-grained selection can improve the performance across perception, prediction, and downstream planning tasks.
  arXiv  Detail & Related papers  (2021-04-08T17:57:41Z)
• Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehicles [3.673699859949693]
  A unified framework is proposed to generate corner cases for the decision-making systems. Deep reinforcement learning techniques are applied to learn the behavior policy of background vehicles. With the learned policy, BVs will behave and interact with the CAVs more aggressively, resulting in more corner cases.
  arXiv  Detail & Related papers  (2021-02-06T02:48:23Z)
• Corner case data description and detection [3.4954795813842185]
  Corner cases and related detection are crucial in AI quality assurance for constructing safety- and security-critical systems. One is to enhance DL models robustness to corner case data via the adjustment on parameters/structure. The other is to generate new corner cases for model retraining and improvement. This paper proposes to a simple and novel study aiming at corner case data detection via a specific metric.
  arXiv  Detail & Related papers  (2021-01-07T11:26:20Z)
• AutoAssign: Differentiable Label Assignment for Dense Object Detection [94.24431503373884]
  Auto COCO is an anchor-free detector for object detection. It achieves appearance-aware through a fully differentiable weighting mechanism. Our best model achieves 52.1% AP, outperforming all existing one-stage detectors.
  arXiv  Detail & Related papers  (2020-07-07T14:32:21Z)
• Efficient statistical validation with edge cases to evaluate Highly Automated Vehicles [6.198523595657983]
  The widescale deployment of Autonomous Vehicles seems to be imminent despite many safety challenges that are yet to be resolved. Existing standards focus on deterministic processes where the validation requires only a set of test cases that cover the requirements. This paper presents a new approach to compute the statistical characteristics of a system's behaviour by biasing automatically generated test cases towards the worst case scenarios.
  arXiv  Detail & Related papers  (2020-03-04T04:35:22Z)

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.