PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions

• URL: http://arxiv.org/abs/2307.14070v2
• Date: Mon, 16 Oct 2023 02:33:45 GMT
• Title: PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions
• Authors: Wenjie Xuan, Shanshan Zhao, Yu Yao, Juhua Liu, Tongliang Liu, Yixin Chen, Bo Du, Dacheng Tao
• Abstract summary: It is hard to manually label edges accurately, especially for large datasets. This paper proposes to learn Pixel-level NoiseTransitions to model the label-corruption process.
• Score: 119.17602768128806
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Relying on large-scale training data with pixel-level labels, previous edge detection methods have achieved high performance. However, it is hard to manually label edges accurately, especially for large datasets, and thus the datasets inevitably contain noisy labels. This label-noise issue has been studied extensively for classification, while still remaining under-explored for edge detection. To address the label-noise issue for edge detection, this paper proposes to learn Pixel-level NoiseTransitions to model the label-corruption process. To achieve it, we develop a novel Pixel-wise Shift Learning (PSL) module to estimate the transition from clean to noisy labels as a displacement field. Exploiting the estimated noise transitions, our model, named PNT-Edge, is able to fit the prediction to clean labels. In addition, a local edge density regularization term is devised to exploit local structure information for better transition learning. This term encourages learning large shifts for the edges with complex local structures. Experiments on SBD and Cityscapes demonstrate the effectiveness of our method in relieving the impact of label noise. Codes are available at https://github.com/DREAMXFAR/PNT-Edge.

Related papers

• ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance [53.73316938815873]
  We propose a method called ERASE (Error-Resilient representation learning on graphs for lAbel noiSe tolerancE) to learn representations with error tolerance. ERASE combines prototype pseudo-labels with propagated denoised labels and updates representations with error resilience. Our method can outperform multiple baselines with clear margins in broad noise levels and enjoy great scalability.
  arXiv  Detail & Related papers  (2023-12-13T17:59:07Z)
• Accurate Segmentation of Optic Disc And Cup from Multiple Pseudo-labels by Noise-aware Learning [16.09436396639938]
  We propose an innovative label-denoising method of Multiple Pseudo-labels Noise-aware Network (MPNN) for accurate optic disc and cup segmentation. Specifically, the MPNN generates pseudo-labels by multiple different networks trained on true labels, and the pixel-level consensus information extracted from these pseudo-labels guides. The training framework of the MPNN is constructed by a teacher-student architecture to learn segmentation from clean pixels and noisy pixels.
  arXiv  Detail & Related papers  (2023-11-30T12:17:16Z)
• Robust Point Cloud Segmentation with Noisy Annotations [32.991219357321334]
  Class labels are often mislabeled at both instance-level and boundary-level in real-world datasets. We take the lead in solving the instance-level label noise by proposing a Point Noise-Adaptive Learning framework. Our framework significantly outperforms its baselines, and is comparable to the upper bound trained on completely clean data.
  arXiv  Detail & Related papers  (2022-12-06T18:59:58Z)
• Instance-dependent Label-noise Learning under a Structural Causal Model [92.76400590283448]
  Label noise will degenerate the performance of deep learning algorithms. By leveraging a structural causal model, we propose a novel generative approach for instance-dependent label-noise learning.
  arXiv  Detail & Related papers  (2021-09-07T10:42:54Z)
• Robust Long-Tailed Learning under Label Noise [50.00837134041317]
  This work investigates the label noise problem under long-tailed label distribution. We propose a robust framework,algo, that realizes noise detection for long-tailed learning. Our framework can naturally leverage semi-supervised learning algorithms to further improve the generalisation.
  arXiv  Detail & Related papers  (2021-08-26T03:45:00Z)
• Learning with Noisy Labels for Robust Point Cloud Segmentation [22.203927159777123]
  Object class labels are often mislabeled in real-world point cloud datasets. We propose a novel Point Noise-Adaptive Learning (PNAL) framework. We conduct extensive experiments to demonstrate the effectiveness of PNAL on both synthetic and real-world noisy datasets.
  arXiv  Detail & Related papers  (2021-07-29T17:59:54Z)
• Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation [12.937770890847819]
  We propose a graph based label noise detection and correction framework to deal with pixel-level noisy labels. In particular, for the generated pixel-level noisy labels from weak supervisions by Class Activation Map (CAM), we train a clean segmentation model with strong supervisions. Finally, we adopt a superpixel-based graph to represent the relations of spatial adjacency and semantic similarity between pixels in one image.
  arXiv  Detail & Related papers  (2021-03-26T03:23:21Z)
• Uncertainty-based method for improving poorly labeled segmentation datasets [0.0]
  It is known that deep convolutional neural networks (DCNNs) can memorize even completely random labels. We propose a framework to train binary segmentation DCNNs using sets of unreliable pixel-level annotations.
  arXiv  Detail & Related papers  (2021-02-16T08:37:19Z)
• 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)
• Attention-Aware Noisy Label Learning for Image Classification [97.26664962498887]
  Deep convolutional neural networks (CNNs) learned on large-scale labeled samples have achieved remarkable progress in computer vision. The cheapest way to obtain a large body of labeled visual data is to crawl from websites with user-supplied labels, such as Flickr. This paper proposes the attention-aware noisy label learning approach to improve the discriminative capability of the network trained on datasets with potential label noise.
  arXiv  Detail & Related papers  (2020-09-30T15:45:36Z)

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.