Hard Samples, Bad Labels: Robust Loss Functions That Know When to Back Off

• URL: http://arxiv.org/abs/2511.16512v2
• Date: Tue, 25 Nov 2025 21:42:49 GMT
• Title: Hard Samples, Bad Labels: Robust Loss Functions That Know When to Back Off
• Authors: Nicholas Pellegrino, David Szczecina, Paul Fieguth,
• Abstract summary: Incorrectly labelled training data adversely affects the performance and generalizability of models trained through supervised learning.<n>We evaluate two novel loss functions, Blurry Loss and Piecewise-zero Loss, that enhance robustness to label errors by de-weighting or disregarding difficult-to-classify samples.
• Score: 1.1582652820340928
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Incorrectly labelled training data are frustratingly ubiquitous in both benchmark and specially curated datasets. Such mislabelling clearly adversely affects the performance and generalizability of models trained through supervised learning on the associated datasets. Frameworks for detecting label errors typically require well-trained / well-generalized models; however, at the same time most frameworks rely on training these models on corrupt data, which clearly has the effect of reducing model generalizability and subsequent effectiveness in error detection -- unless a training scheme robust to label errors is employed. We evaluate two novel loss functions, Blurry Loss and Piecewise-zero Loss, that enhance robustness to label errors by de-weighting or disregarding difficult-to-classify samples, which are likely to be erroneous. These loss functions leverage the idea that mislabelled examples are typically more difficult to classify and should contribute less to the learning signal. Comprehensive experiments on a variety of artificially corrupted datasets demonstrate that the proposed loss functions outperform state-of-the-art robust loss functions in nearly all cases, achieving superior F1 scores for error detection. Further analyses through ablation studies offer insights to confirm these loss functions' broad applicability to cases of both uniform and non-uniform corruption, and with different label error detection frameworks. By using these robust loss functions, machine learning practitioners can more effectively identify, prune, or correct errors in their training data.

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories [11.597228102492672]
  We propose a model-agnostic method for detecting annotation errors in video datasets.<n>Our method does not require ground truth on annotation errors and is generalizable across datasets.<n>EgoPER and Cholec80 demonstrate strong detection performance, effectively identifying subtle inconsistencies such as mislabeling and frame disordering.
  arXiv  Detail & Related papers  (2026-02-16T19:53:58Z)
• Unsupervised Learning for Industrial Defect Detection: A Case Study on Shearographic Data [0.0]
  This study explores unsupervised learning methods for automated anomaly detection in shearographic images.<n>Three architectures are evaluated: a fully connected autoencoder, a convolutional autoencoder, and a student-teacher model.<n>Results show that the student-teacher approach achieves superior classification and enables precise localization.
  arXiv  Detail & Related papers  (2025-11-04T12:48:02Z)
• Detecting and Rectifying Noisy Labels: A Similarity-based Approach [4.686586017523293]
  Label noise in datasets could significantly damage the performance and robustness of deep neural networks (DNNs) trained on these datasets.<n>We propose post-hoc, model-agnostic noise detection and rectification methods utilizing the penultimate feature from a DNN.<n>Our idea is based on the observation that the similarity between the penultimate feature of a mislabeled data point and its true class data points is higher than that for data points from other classes.
  arXiv  Detail & Related papers  (2025-09-28T16:41:56Z)
• Improving Label Error Detection and Elimination with Uncertainty Quantification [5.184615738004059]
  We develop novel, model-agnostic algorithms for Uncertainty Quantification-Based Label Error Detection (UQ-LED) Our UQ-LED algorithms outperform state-of-the-art confident learning in identifying label errors. We propose a novel approach to generate realistic, class-dependent label errors synthetically.
  arXiv  Detail & Related papers  (2024-05-15T15:17:52Z)
• Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening [51.34904967046097]
  We introduce an extension to the selective synaptic dampening unlearning method that removes the need for parameter tuning. We demonstrate the performance of this extension, adaptive selective synaptic dampening (ASSD) on various ResNet18 and Vision Transformer unlearning tasks. The application of this approach is particularly compelling in industrial settings, such as supply chain management.
  arXiv  Detail & Related papers  (2024-02-06T14:04:31Z)
• Late Stopping: Avoiding Confidently Learning from Mislabeled Examples [61.00103151680946]
  We propose a new framework, Late Stopping, which leverages the intrinsic robust learning ability of DNNs through a prolonged training process. We empirically observe that mislabeled and clean examples exhibit differences in the number of epochs required for them to be consistently and correctly classified. Experimental results on benchmark-simulated and real-world noisy datasets demonstrate that the proposed method outperforms state-of-the-art counterparts.
  arXiv  Detail & Related papers  (2023-08-26T12:43:25Z)
• Defect detection using weakly supervised learning [1.4321190258774352]
  Weakly supervised learning techniques have gained significant attention in recent years as an alternative to traditional supervised learning. In this paper, the performance of a weakly supervised classifier to its fully supervised counterpart is compared on the task of defect detection.
  arXiv  Detail & Related papers  (2023-03-27T11:01:16Z)
• Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
  Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data. We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
  arXiv  Detail & Related papers  (2023-03-06T14:49:59Z)
• PULL: Reactive Log Anomaly Detection Based On Iterative PU Learning [58.85063149619348]
  We propose PULL, an iterative log analysis method for reactive anomaly detection based on estimated failure time windows. Our evaluation shows that PULL consistently outperforms ten benchmark baselines across three different datasets.
  arXiv  Detail & Related papers  (2023-01-25T16:34:43Z)
• Losses over Labels: Weakly Supervised Learning via Direct Loss Construction [71.11337906077483]
  Programmable weak supervision is a growing paradigm within machine learning. We propose Losses over Labels (LoL) as it creates losses directly from ofs without going through the intermediate step of a label. We show that LoL improves upon existing weak supervision methods on several benchmark text and image classification tasks.
  arXiv  Detail & Related papers  (2022-12-13T22:29:14Z)
• CTRL: Clustering Training Losses for Label Error Detection [4.49681473359251]
  In supervised machine learning, use of correct labels is extremely important to ensure high accuracy. We propose a novel framework, calledClustering TRaining Losses for label error detection. It detects label errors in two steps based on the observation that models learn clean and noisy labels in different ways.
  arXiv  Detail & Related papers  (2022-08-17T18:09:19Z)
• Repairing Neural Networks by Leaving the Right Past Behind [23.78437548836594]
  Prediction failures of machine learning models often arise from deficiencies in training data. This work develops a generic framework for both identifying training examples that have given rise to the target failure, and fixing the model through erasing information about them.
  arXiv  Detail & Related papers  (2022-07-11T12:07:39Z)
• Prototype-Anchored Learning for Learning with Imperfect Annotations [83.7763875464011]
  It is challenging to learn unbiased classification models from imperfectly annotated datasets. We propose a prototype-anchored learning (PAL) method, which can be easily incorporated into various learning-based classification schemes. We verify the effectiveness of PAL on class-imbalanced learning and noise-tolerant learning by extensive experiments on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2022-06-23T10:25:37Z)
• Detecting Label Errors using Pre-Trained Language Models [37.82128817976385]
  We show that large pre-trained language models are extremely capable of identifying label errors in datasets. We contribute a novel method to produce highly realistic, human-originated label noise from crowdsourced data, and demonstrate the effectiveness of this method on TweetNLP.
  arXiv  Detail & Related papers  (2022-05-25T11:59:39Z)
• SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation [77.71161225100927]
  Anomaly detection is a fundamental yet challenging problem in machine learning. We propose a novel and powerful framework, dubbed as SLA$2$P, for unsupervised anomaly detection.
  arXiv  Detail & Related papers  (2021-11-25T03:53:43Z)
• Sample Selection with Uncertainty of Losses for Learning with Noisy Labels [145.06552420999986]
  In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-the-fly based on the model being trained with noisy labels, and thus large-loss data are likely but not certainly to be incorrect. In this paper, we incorporate the uncertainty of losses by adopting interval estimation instead of point estimation of losses.
  arXiv  Detail & Related papers  (2021-06-01T12:53:53Z)
• Improving Generalization of Deep Fault Detection Models in the Presence of Mislabeled Data [1.3535770763481902]
  We propose a novel two-step framework for robust training with label noise. In the first step, we identify outliers (including the mislabeled samples) based on the update in the hypothesis space. In the second step, we propose different approaches to modifying the training data based on the identified outliers and a data augmentation technique.
  arXiv  Detail & Related papers  (2020-09-30T12:33:25Z)
• Salvage Reusable Samples from Noisy Data for Robust Learning [70.48919625304]
  We propose a reusable sample selection and correction approach, termed as CRSSC, for coping with label noise in training deep FG models with web images. Our key idea is to additionally identify and correct reusable samples, and then leverage them together with clean examples to update the networks.
  arXiv  Detail & Related papers  (2020-08-06T02:07:21Z)
• Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets [98.74153364118898]
  We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions. The Distribution-Balanced Loss tackles these issues through two key modifications to the standard binary cross-entropy loss. Experiments on both Pascal VOC and COCO show that the models trained with this new loss function achieve significant performance gains.
  arXiv  Detail & Related papers  (2020-07-19T11:50:10Z)

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.