DIRECT: Deep Active Learning under Imbalance and Label Noise

• URL: http://arxiv.org/abs/2312.09196v3
• Date: Mon, 20 May 2024 15:06:18 GMT
• Title: DIRECT: Deep Active Learning under Imbalance and Label Noise
• Authors: Shyam Nuggehalli, Jifan Zhang, Lalit Jain, Robert Nowak,
• Abstract summary: We conduct the first study of active learning under both class imbalance and label noise. We propose a novel algorithm that robustly identifies the class separation threshold and annotates the most uncertain examples. Our results demonstrate that DIRECT can save more than 60% of the annotation budget compared to state-of-art active learning algorithms.
• Score: 15.571923343398657
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Class imbalance is a prevalent issue in real world machine learning applications, often leading to poor performance in rare and minority classes. With an abundance of wild unlabeled data, active learning is perhaps the most effective technique in solving the problem at its root -- collecting a more balanced and informative set of labeled examples during annotation. Label noise is another common issue in data annotation jobs, which is especially challenging for active learning methods. In this work, we conduct the first study of active learning under both class imbalance and label noise. We propose a novel algorithm that robustly identifies the class separation threshold and annotates the most uncertain examples that are closest from it. Through a novel reduction to one-dimensional active learning, our algorithm DIRECT is able to leverage the classic active learning literature to address issues such as batch labeling and tolerance towards label noise. We present extensive experiments on imbalanced datasets with and without label noise. Our results demonstrate that DIRECT can save more than 60% of the annotation budget compared to state-of-art active learning algorithms and more than 80% of annotation budget compared to random sampling.

Related papers

• Multiclass Learning from Noisy Labels for Non-decomposable Performance Measures [15.358504449550013]
  We design algorithms to learn from noisy labels for two broad classes of non-decomposable performance measures. In both cases, we develop noise-corrected versions of the algorithms under the widely studied class-conditional noise models. Our experiments demonstrate the effectiveness of our algorithms in handling label noise.
  arXiv  Detail & Related papers  (2024-02-01T23:03:53Z)
• Robust Assignment of Labels for Active Learning with Sparse and Noisy Annotations [0.17188280334580192]
  Supervised classification algorithms are used to solve a growing number of real-life problems around the globe. Unfortunately, acquiring good-quality annotations for many tasks is infeasible or too expensive to be done in practice. We propose two novel annotation unification algorithms that utilize unlabeled parts of the sample space.
  arXiv  Detail & Related papers  (2023-07-25T19:40:41Z)
• Unleashing the Potential of Regularization Strategies in Learning with Noisy Labels [65.92994348757743]
  We demonstrate that a simple baseline using cross-entropy loss, combined with widely used regularization strategies can outperform state-of-the-art methods. Our findings suggest that employing a combination of regularization strategies can be more effective than intricate algorithms in tackling the challenges of learning with noisy labels.
  arXiv  Detail & Related papers  (2023-07-11T05:58:20Z)
• Co-Learning Meets Stitch-Up for Noisy Multi-label Visual Recognition [70.00984078351927]
  This paper focuses on reducing noise based on some inherent properties of multi-label classification and long-tailed learning under noisy cases. We propose a Stitch-Up augmentation to synthesize a cleaner sample, which directly reduces multi-label noise. A Heterogeneous Co-Learning framework is further designed to leverage the inconsistency between long-tailed and balanced distributions.
  arXiv  Detail & Related papers  (2023-07-03T09:20:28Z)
• Prototypical Classifier for Robust Class-Imbalanced Learning [64.96088324684683]
  We propose textitPrototypical, which does not require fitting additional parameters given the embedding network. Prototypical produces balanced and comparable predictions for all classes even though the training set is class-imbalanced. We test our method on CIFAR-10LT, CIFAR-100LT and Webvision datasets, observing that Prototypical obtains substaintial improvements compared with state of the arts.
  arXiv  Detail & Related papers  (2021-10-22T01:55:01Z)
• 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 From Long-Tailed Data With Noisy Labels [0.0]
  Class imbalance and noisy labels are the norm in many large-scale classification datasets. We present a simple two-stage approach based on recent advances in self-supervised learning. We find that self-supervised learning approaches are effectively able to cope with severe class imbalance.
  arXiv  Detail & Related papers  (2021-08-25T07:45:40Z)
• Open-set Label Noise Can Improve Robustness Against Inherent Label Noise [27.885927200376386]
  We show that open-set noisy labels can be non-toxic and even benefit the robustness against inherent noisy labels. We propose a simple yet effective regularization by introducing Open-set samples with Dynamic Noisy Labels (ODNL) into training.
  arXiv  Detail & Related papers  (2021-06-21T07:15:50Z)
• A Second-Order Approach to Learning with Instance-Dependent Label Noise [58.555527517928596]
  The presence of label noise often misleads the training of deep neural networks. We show that the errors in human-annotated labels are more likely to be dependent on the difficulty levels of tasks.
  arXiv  Detail & Related papers  (2020-12-22T06:36:58Z)
• Efficient PAC Learning from the Crowd with Pairwise Comparison [7.594050968868919]
  We study the problem of PAC learning threshold functions from the crowd, where the annotators can provide (noisy) labels or pairwise comparison tags. We design a label-efficient algorithm that interleaves learning and annotation, which leads to a constant overhead of our algorithm.
  arXiv  Detail & Related papers  (2020-11-02T16:37:55Z)
• Active Learning under Label Shift [80.65643075952639]
  We introduce a "medial distribution" to incorporate a tradeoff between importance and class-balanced sampling. We prove sample complexity and generalization guarantees for Mediated Active Learning under Label Shift (MALLS) We empirically demonstrate MALLS scales to high-dimensional datasets and can reduce the sample complexity of active learning by 60% in deep active learning tasks.
  arXiv  Detail & Related papers  (2020-07-16T17:30:02Z)

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.