Pseudo-Label Ensemble-based Semi-supervised Learning for Handling Noisy Soiling Segmentation Annotations

• URL: http://arxiv.org/abs/2105.07930v1
• Date: Mon, 17 May 2021 15:10:00 GMT
• Title: Pseudo-Label Ensemble-based Semi-supervised Learning for Handling Noisy Soiling Segmentation Annotations
• Abstract summary: We train a soiling segmentation model on both noisy and refined labels. It also illustrates that it is possible to effectively refine lower cost coarse annotations.
• Score: 2.5638982073427568
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Manual annotation of soiling on surround view cameras is a very challenging and expensive task. The unclear boundary for various soiling categories like water drops or mud particles usually results in a large variance in the annotation quality. As a result, the models trained on such poorly annotated data are far from being optimal. In this paper, we focus on handling such noisy annotations via pseudo-label driven ensemble model which allow us to quickly spot problematic annotations and in most cases also sufficiently fixing them. We train a soiling segmentation model on both noisy and refined labels and demonstrate significant improvements using the refined annotations. It also illustrates that it is possible to effectively refine lower cost coarse annotations.

Related papers

• PaSta: Noisy Node Classification with Partial Label Learning [58.43127707101144]
  We propose a novel Partial label-based Self-training framework to overcome the limitations of existing methods.<n>PaSta achieves an average improvement of 1.1% in classification performance under various noise settings.
  arXiv  Detail & Related papers  (2026-08-26T04:40:23Z)
• Noisy Annotations in Semantic Segmentation [5.139071616097179]
  This study sheds light on the quality of segmentation masks produced by various models. It challenges the efficacy of popular methods designed to address learning with label noise.
  arXiv  Detail & Related papers  (2024-06-16T10:49:23Z)
• How to Efficiently Annotate Images for Best-Performing Deep Learning Based Segmentation Models: An Empirical Study with Weak and Noisy Annotations and Segment Anything Model [18.293057751504122]
  Deep neural networks (DNNs) have been deployed for many image segmentation tasks and achieved outstanding performance. preparing a dataset for training segmentations is laborious and costly since typically pixel-level annotations are provided for each object of interest. To alleviate this issue, one can provide only weak labels such as bounding boxes or scribbles, or less accurate (noisy) annotations of the objects.
  arXiv  Detail & Related papers  (2023-12-17T04:26:42Z)
• Learning to Segment from Noisy Annotations: A Spatial Correction Approach [12.604673584405385]
  Noisy labels can significantly affect the performance of deep neural networks (DNNs) We propose a novel Markov model for segmentation noisy annotations that encodes both spatial correlation and bias. Our approach outperforms current state-of-the-art methods on both synthetic and real-world noisy annotations.
  arXiv  Detail & Related papers  (2023-07-21T00:27:40Z)
• Robust Feature Learning Against Noisy Labels [0.2082426271304908]
  Mislabeled samples can significantly degrade the generalization of models. progressive self-bootstrapping is introduced to minimize the negative impact of supervision from noisy labels. Experimental results show that our proposed method can efficiently and effectively enhance model robustness under severely noisy labels.
  arXiv  Detail & Related papers  (2023-07-10T02:55:35Z)
• Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation [107.72926721837726]
  coarse annotation is a low-cost but highly effective alternative for training semantic segmentation models. We propose a coarse-to-fine self-training framework that generates pseudo labels for unlabeled regions of coarsely annotated data. Our method achieves a significantly better performance vs annotation cost tradeoff, yielding a comparable performance to fully annotated data with only a small fraction of the annotation budget.
  arXiv  Detail & Related papers  (2022-12-15T15:43:42Z)
• SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining [76.95808270536318]
  We propose an end-to-end system that learns to separate proposals into labeled and unlabeled regions using Pseudo-positive mining. While the labeled regions are processed as usual, self-supervised learning is used to process the unlabeled regions. We conduct exhaustive experiments on five splits on the PASCAL-VOC and COCO datasets achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-01-12T18:57:04Z)
• Noisy Annotation Refinement for Object Detection [47.066070566714984]
  We propose a new problem setting of training object detectors on datasets with entangled noises of annotations of class labels and bounding boxes. Our proposed method efficiently decouples the entangled noises, corrects the noisy annotations, and subsequently trains the detector using the corrected annotations.
  arXiv  Detail & Related papers  (2021-10-20T09:39:50Z)
• Learning with Noisy Labels by Targeted Relabeling [52.0329205268734]
  Crowdsourcing platforms are often used to collect datasets for training deep neural networks. We propose an approach which reserves a fraction of annotations to explicitly relabel highly probable labeling errors.
  arXiv  Detail & Related papers  (2021-10-15T20:37:29Z)
• Noisy Labels Can Induce Good Representations [53.47668632785373]
  We study how architecture affects learning with noisy labels. We show that training with noisy labels can induce useful hidden representations, even when the model generalizes poorly. This finding leads to a simple method to improve models trained on noisy labels.
  arXiv  Detail & Related papers  (2020-12-23T18:58:05Z)
• Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning [80.20302993614594]
  We provide a statistical analysis to overcome drawbacks of Laplacian regularization. We unveil a large body of spectral filtering methods that exhibit desirable behaviors. We provide realistic computational guidelines in order to make our method usable with large amounts of data.
  arXiv  Detail & Related papers  (2020-09-09T14:28:54Z)
• Improving Training on Noisy Stuctured Labels [17.835042432662846]
  We propose a novel framework of Error-Correcting Networks (ECN) to address the challenge of learning in the presence structured error in fine-grained annotations. ECN substantially improves the prediction of fine-grained annotations compared to standard approaches for training on noisy data.
  arXiv  Detail & Related papers  (2020-03-08T22:55:11Z)

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.