Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification

• URL: http://arxiv.org/abs/2111.00928v1
• Date: Mon, 1 Nov 2021 13:23:42 GMT
• Title: Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification
• Authors: Zhenyu Wang, Yali Li, Ye Guo, Shengjin Wang
• Abstract summary: Current methods are easily distracted by noisy regions generated by pseudo labels. We propose noise-resistant semi-supervised learning by quantifying the region uncertainty. Experiments on both PASCAL VOC and MS COCO demonstrate the extraordinary performance of our method.
• Score: 55.23467274564417
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semi-supervised learning aims to leverage a large amount of unlabeled data for performance boosting. Existing works primarily focus on image classification. In this paper, we delve into semi-supervised learning for object detection, where labeled data are more labor-intensive to collect. Current methods are easily distracted by noisy regions generated by pseudo labels. To combat the noisy labeling, we propose noise-resistant semi-supervised learning by quantifying the region uncertainty. We first investigate the adverse effects brought by different forms of noise associated with pseudo labels. Then we propose to quantify the uncertainty of regions by identifying the noise-resistant properties of regions over different strengths. By importing the region uncertainty quantification and promoting multipeak probability distribution output, we introduce uncertainty into training and further achieve noise-resistant learning. Experiments on both PASCAL VOC and MS COCO demonstrate the extraordinary performance of our method.

Related papers

• Training Gradient Boosted Decision Trees on Tabular Data Containing Label Noise for Classification Tasks [1.261491746208123]
  This study aims to investigate the effects of label noise on gradient-boosted decision trees and methods to mitigate those effects. The implemented methods demonstrate state-of-the-art noise detection performance on the Adult dataset and achieve the highest classification precision and recall on the Adult and Breast Cancer datasets.
  arXiv  Detail & Related papers  (2024-09-13T09:09:24Z)
• A noisy elephant in the room: Is your out-of-distribution detector robust to label noise? [49.88894124047644]
  We take a closer look at 20 state-of-the-art OOD detection methods. We show that poor separation between incorrectly classified ID samples vs. OOD samples is an overlooked yet important limitation of existing methods.
  arXiv  Detail & Related papers  (2024-04-02T09:40:22Z)
• Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective [38.24239397999152]
  We propose a novel sample selection-based approach for noisy label learning, called Proto-semi. Proto-semi divides all samples into the confident and unconfident datasets via warm-up. By leveraging the confident dataset, prototype vectors are constructed to capture class characteristics. Empirical evaluations on a real-world annotated dataset substantiate the robustness of Proto-semi in handling the problem of learning from noisy labels.
  arXiv  Detail & Related papers  (2023-07-28T10:57:38Z)
• MuRAL: Multi-Scale Region-based Active Learning for Object Detection [20.478741635006116]
  We propose a novel approach called Multi-scale Region-based Active Learning (MuRAL) for object detection. MuRAL identifies informative regions of various scales to reduce annotation costs for well-learned objects. Our proposed method surpasses all existing coarse-grained and fine-grained baselines on Cityscapes and MS COCO datasets.
  arXiv  Detail & Related papers  (2023-03-29T12:52:27Z)
• Learning with Noisy Labels through Learnable Weighting and Centroid Similarity [5.187216033152917]
  noisy labels are prevalent in domains such as medical diagnosis and autonomous driving. We introduce a novel method for training machine learning models in the presence of noisy labels. Our results show that our method consistently outperforms the existing state-of-the-art techniques.
  arXiv  Detail & Related papers  (2023-03-16T16:43:24Z)
• Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection [66.10057490293981]
  We propose a data-uncertainty guided multi-phase learning method for semi-supervised object detection. Our method behaves extraordinarily compared to baseline approaches and outperforms them by a large margin.
  arXiv  Detail & Related papers  (2021-03-29T09:27:23Z)
• Improving Face Recognition by Clustering Unlabeled Faces in the Wild [77.48677160252198]
  We propose a novel identity separation method based on extreme value theory. It greatly reduces the problems caused by overlapping-identity label noise. Experiments on both controlled and real settings demonstrate our method's consistent improvements.
  arXiv  Detail & Related papers  (2020-07-14T12:26:50Z)
• Towards Noise-resistant Object Detection with Noisy Annotations [119.63458519946691]
  Training deep object detectors requires significant amount of human-annotated images with accurate object labels and bounding box coordinates. Noisy annotations are much more easily accessible, but they could be detrimental for learning. We address the challenging problem of training object detectors with noisy annotations, where the noise contains a mixture of label noise and bounding box noise.
  arXiv  Detail & Related papers  (2020-03-03T01:32:16Z)
• Learning Not to Learn in the Presence of Noisy Labels [104.7655376309784]
  We show that a new class of loss functions called the gambler's loss provides strong robustness to label noise across various levels of corruption. We show that training with this loss function encourages the model to "abstain" from learning on the data points with noisy labels.
  arXiv  Detail & Related papers  (2020-02-16T09:12:27Z)

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.