Benchmarking Instance-Dependent Label Noise with Controlled Corruptions

• URL: http://arxiv.org/abs/2606.14965v1
• Date: Fri, 12 Jun 2026 21:30:18 GMT
• Title: Benchmarking Instance-Dependent Label Noise with Controlled Corruptions
• Abstract summary: We introduce CILN, a benchmark generation framework that creates IDN through controlled input corruptions.<n>A diverse voter pool labels corrupted instances, producing benchmark in which both the source and severity of ambiguity are explicit and controllable.<n>Our experiments show that the resulting benchmarks exhibit genuine instance-dependent noise, provide diverse confusion structures, and, on CIFAR-10, can produce label distributions closer to human uncertainty than an existing synthetic IDN benchmark.
• Score: 5.23162679530451
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Synthetic instance-dependent label noise (IDN) benchmarks are widely used to evaluate noisy-label learning methods, yet existing approaches typically generate noise through imperfect annotators or classifier raters, leaving the source of ambiguity implicit. We introduce CILN, a benchmark generation framework that creates IDN through controlled input corruptions. A diverse voter pool labels corrupted instances, producing benchmark datasets in which both the source and severity of ambiguity are explicit and controllable. Using CIFAR10, MNIST, and Adult, we construct 90 benchmark settings spanning multiple corruption families and severity levels. Our experiments show that the resulting benchmarks exhibit genuine instance-dependent noise, provide diverse confusion structures, and, on CIFAR-10, can produce label distributions that are closer to human uncertainty than an existing synthetic IDN benchmark. We further demonstrate that corruption-mediated IDN can expose failure modes of popular noisy-label learning methods, including Co-Teaching and DivideMix, that are not observed under comparable levels of rater-fallibility noise. These findings suggest that noise structure, not only noise rate, plays an important role in benchmark difficulty and algorithm behavior. By making ambiguity generation explicit and controllable, CILN provides a complementary benchmarking framework for studying noisy-label learning under diverse sources of instance difficulty.

Related papers

• Test-time Adaptive Hierarchical Co-enhanced Denoising Network for Reliable Multimodal Classification [55.56234913868664]
  We propose Test-time Adaptive Hierarchical Co-enhanced Denoising Network (TAHCD) for reliable learning on multimodal data.<n>The proposed method achieves superior classification performance, robustness, and generalization compared with state-of-the-art reliable multimodal learning approaches.
  arXiv  Detail & Related papers  (2026-01-12T03:14:12Z)
• Mitigating Instance-Dependent Label Noise: Integrating Self-Supervised Pretraining with Pseudo-Label Refinement [3.272177633069322]
  Real-world datasets often contain noisy labels due to human error, ambiguity, or resource constraints during the annotation process.<n>We propose a novel framework that combines self-supervised learning using SimCLR with iterative pseudo-label refinement.<n>Our approach significantly outperforms several state-of-the-art methods, particularly under high noise conditions.
  arXiv  Detail & Related papers  (2024-12-06T09:56:49Z)
• NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing [26.678589684142548]
  Large-scale datasets in the real world inevitably involve label noise. Deep models can gradually overfit noisy labels and thus degrade generalization performance. To mitigate the effects of label noise, learning with noisy labels (LNL) methods are designed to achieve better generalization performance.
  arXiv  Detail & Related papers  (2023-05-18T05:01:04Z)
• Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling [22.62790706276081]
  Training deep neural network (DNN) with noisy labels is practically challenging. Previous efforts tend to handle part or full data in a unified denoising flow. We propose a coarse-to-fine robust learning method called CREMA to handle noisy data in a divide-and-conquer manner.
  arXiv  Detail & Related papers  (2022-08-23T02:06:38Z)
• Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations [54.400167806154535]
  Existing research on learning with noisy labels mainly focuses on synthetic label noise. This work presents two new benchmark datasets (CIFAR-10N, CIFAR-100N) We show that real-world noisy labels follow an instance-dependent pattern rather than the classically adopted class-dependent ones.
  arXiv  Detail & Related papers  (2021-10-22T22:42:11Z)
• 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)
• Approximating Instance-Dependent Noise via Instance-Confidence Embedding [87.65718705642819]
  Label noise in multiclass classification is a major obstacle to the deployment of learning systems. We investigate the instance-dependent noise (IDN) model and propose an efficient approximation of IDN to capture the instance-specific label corruption.
  arXiv  Detail & Related papers  (2021-03-25T02:33:30Z)
• Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model [80.91927573604438]
  This paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness.
  arXiv  Detail & Related papers  (2021-01-14T05:43:51Z)
• 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)
• Confidence Scores Make Instance-dependent Label-noise Learning Possible [129.84497190791103]
  In learning with noisy labels, for every instance, its label can randomly walk to other classes following a transition distribution which is named a noise model. We introduce confidence-scored instance-dependent noise (CSIDN), where each instance-label pair is equipped with a confidence score. We find with the help of confidence scores, the transition distribution of each instance can be approximately estimated.
  arXiv  Detail & Related papers  (2020-01-11T16:15:41Z)

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.