FSNet: A Failure Detection Framework for Semantic Segmentation

• URL: http://arxiv.org/abs/2108.08748v1
• Date: Thu, 19 Aug 2021 15:26:52 GMT
• Title: FSNet: A Failure Detection Framework for Semantic Segmentation
• Authors: Quazi Marufur Rahman, Niko S\"underhauf, Peter Corke and Feras Dayoub
• Abstract summary: We propose a failure detection framework to identify pixel-level misclassification. We do so by exploiting internal features of the segmentation model and training it simultaneously with a failure detection network. We evaluate the proposed approach against state-of-the-art methods and achieve 12.30%, 9.46%, and 9.65% performance improvement.
• Score: 9.453250122818808
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semantic segmentation is an important task that helps autonomous vehicles understand their surroundings and navigate safely. During deployment, even the most mature segmentation models are vulnerable to various external factors that can degrade the segmentation performance with potentially catastrophic consequences for the vehicle and its surroundings. To address this issue, we propose a failure detection framework to identify pixel-level misclassification. We do so by exploiting internal features of the segmentation model and training it simultaneously with a failure detection network. During deployment, the failure detector can flag areas in the image where the segmentation model have failed to segment correctly. We evaluate the proposed approach against state-of-the-art methods and achieve 12.30%, 9.46%, and 9.65% performance improvement in the AUPR-Error metric for Cityscapes, BDD100K, and Mapillary semantic segmentation datasets.

Related papers

• Physically Feasible Semantic Segmentation [58.17907376475596]
  State-of-the-art semantic segmentation models are typically optimized in a data-driven fashion. Our method, Physically Feasible Semantic (PhyFea), extracts explicit physical constraints that govern spatial class relations. PhyFea yields significant performance improvements in mIoU over each state-of-the-art network we use.
  arXiv  Detail & Related papers  (2024-08-26T22:39:08Z)
• OoDIS: Anomaly Instance Segmentation Benchmark [57.89836988990543]
  We extend the most commonly used anomaly segmentation benchmarks to include the instance segmentation task. Development in this area has been lagging, largely due to the lack of dedicated benchmarks. Our evaluation of anomaly instance segmentation methods shows that this challenge remains an unsolved problem.
  arXiv  Detail & Related papers  (2024-06-17T17:59:56Z)
• Joint semi-supervised and contrastive learning enables zero-shot domain-adaptation and multi-domain segmentation [1.5393913074555419]
  SegCLR is a versatile framework designed to segment volumetric images across different domains. We demonstrate the superior performance of SegCLR through a comprehensive evaluation.
  arXiv  Detail & Related papers  (2024-05-08T18:10:59Z)
• Uncertainty estimates for semantic segmentation: providing enhanced reliability for automated motor claims handling [0.0]
  We use a meta-classification model to empirically assess the precision of segments predicted by a model trained for the semantic segmentation of car body parts. By removing low-quality segments, the average mIoU of the segmentation output is improved by 16 percentage points and the number of wrongly predicted segments is reduced by 77%.
  arXiv  Detail & Related papers  (2024-01-17T14:47:26Z)
• UGainS: Uncertainty Guided Anomaly Instance Segmentation [80.12253291709673]
  A single unexpected object on the road can cause an accident or lead to injuries. Current approaches tackle anomaly segmentation by assigning an anomaly score to each pixel. We propose an approach that produces accurate anomaly instance masks.
  arXiv  Detail & Related papers  (2023-08-03T20:55:37Z)
• CLIP the Gap: A Single Domain Generalization Approach for Object Detection [60.20931827772482]
  Single Domain Generalization tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. We propose to leverage a pre-trained vision-language model to introduce semantic domain concepts via textual prompts. We achieve this via a semantic augmentation strategy acting on the features extracted by the detector backbone, as well as a text-based classification loss.
  arXiv  Detail & Related papers  (2023-01-13T12:01:18Z)
• SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation [111.61261419566908]
  Deep neural networks (DNNs) are usually trained on a closed set of semantic classes. They are ill-equipped to handle previously-unseen objects. detecting and localizing such objects is crucial for safety-critical applications such as perception for automated driving.
  arXiv  Detail & Related papers  (2021-04-30T07:58:19Z)
• Self-supervised Segmentation via Background Inpainting [96.10971980098196]
  We introduce a self-supervised detection and segmentation approach that can work with single images captured by a potentially moving camera. We exploit a self-supervised loss function that we exploit to train a proposal-based segmentation network. We apply our method to human detection and segmentation in images that visually depart from those of standard benchmarks and outperform existing self-supervised methods.
  arXiv  Detail & Related papers  (2020-11-11T08:34:40Z)
• Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation [17.532822703595766]
  We present a novel loss function, called class-agnostic segmentation (CAS) loss. We show that the CAS loss function is sparse, bounded, and robust to class-imbalance. We investigate the performance against the state-of-the-art methods in two settings of low and high-fidelity training data.
  arXiv  Detail & Related papers  (2020-10-28T07:11:15Z)
• ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data [34.36975697486129]
  We present a rarely addressed task regarding semantic segmentation in accidental scenarios, along with an accident dataset DADA-seg. We propose a novel event-based multi-modal segmentation architecture ISSAFE. Our approach achieves +8.2% mIoU performance gain on the proposed evaluation set, exceeding more than 10 state-of-the-art segmentation methods.
  arXiv  Detail & Related papers  (2020-08-20T14:03:34Z)

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.