Step-E: A Differentiable Data Cleaning Framework for Robust Learning with Noisy Labels

• URL: http://arxiv.org/abs/2511.17040v1
• Date: Fri, 21 Nov 2025 08:31:43 GMT
• Title: Step-E: A Differentiable Data Cleaning Framework for Robust Learning with Noisy Labels
• Abstract summary: We propose Step-E, a framework that integrates sample selection and model learning into a single optimization process.<n>Step-E ranks samples by loss and gradually increases the fraction of high-loss examples that are excluded from updates.<n>On CIFAR-100N, Step-E improves the test accuracy of a ResNet-18 model from 43.3% to 50.4%.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training data collected in the wild often contain noisy labels and outliers that substantially degrade the performance and reliability of deep neural networks. While data cleaning is commonly applied as a separate preprocessing stage, such two-stage pipelines neither fully exploit feedback from the downstream model nor adapt to unknown noise patterns. We propose Step-E, a simple framework that integrates sample selection and model learning into a single optimization process. At each epoch, Step-E ranks samples by loss and gradually increases the fraction of high-loss examples that are excluded from gradient updates after a brief warm-up stage, yielding an online curriculum that focuses on easy and consistent examples and eventually ignores persistent outliers. On CIFAR-100N, Step-E improves the test accuracy of a ResNet-18 model from 43.3% (+/- 0.7%) to 50.4% (+/- 0.9%), clearly outperforming loss truncation, self-paced learning, and one-shot filtering while approaching the clean-label oracle at 60.5% (+/- 0.2%). On CIFAR-10N (aggre), Step-E also improves over the noisy baseline (85.3% vs. 83.9%) and nearly matches the clean-label oracle (85.9%), with only moderate training-time overhead.

Related papers

• Pioneer Agent: Continual Improvement of Small Language Models in Production [6.452260317191361]
  Small language models are attractive for production deployment due to their low cost, fast inference, and ease of specialization.<n>We present Pioneer Agent, a closed-loop system that automates the process of adapting small language models to a specific task.
  arXiv  Detail & Related papers  (2026-04-10T18:13:09Z)
• Pre-train to Gain: Robust Learning Without Clean Labels [1.1582652820340928]
  Training deep networks with noisy labels leads to poor generalization and degraded accuracy.<n>By pre-training a feature extractor backbone without labels, we can train a more noise robust model without requiring a subset with clean labels.<n>Our approach achieves comparable results to ImageNet pre-trained models at low noise levels, while substantially outperforming them under high noise conditions.
  arXiv  Detail & Related papers  (2025-11-25T20:48:07Z)
• The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling [78.6155095947769]
  Skip-Tuning is a simple yet surprisingly effective training-free tuning method on the skip connections. Our method can achieve 100% FID improvement for pretrained EDM on ImageNet 64 with only 19 NFEs (1.75) While Skip-Tuning increases the score-matching losses in the pixel space, the losses in the feature space are reduced.
  arXiv  Detail & Related papers  (2024-02-23T08:05:23Z)
• Combating Label Noise With A General Surrogate Model For Sample Selection [77.45468386115306]
  We propose to leverage the vision-language surrogate model CLIP to filter noisy samples automatically.<n>We validate the effectiveness of our proposed method on both real-world and synthetic noisy datasets.
  arXiv  Detail & Related papers  (2023-10-16T14:43:27Z)
• Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning [79.43940012723539]
  ADCLR is a self-supervised learning framework for learning accurate and dense vision representation. Our approach achieves new state-of-the-art performance for contrastive methods.
  arXiv  Detail & Related papers  (2023-06-23T07:38:09Z)
• Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data [122.282521548393]
  Contrastive Language-Image Pre-training (CLIP) has become the standard for cross-modal image-text representation learning.<n>We introduce HELIP, a cost-effective strategy that improves CLIP models by exploiting challenging text-image pairs within existing datasets in continuous training.
  arXiv  Detail & Related papers  (2023-05-09T07:00:17Z)
• Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels [65.79898033530408]
  We introduce a novel framework, termed as LC-Booster, to explicitly tackle learning under extreme noise. LC-Booster incorporates label correction into the sample selection, so that more purified samples, through the reliable label correction, can be utilized for training. Experiments show that LC-Booster advances state-of-the-art results on several noisy-label benchmarks.
  arXiv  Detail & Related papers  (2022-04-30T07:19:03Z)
• CNLL: A Semi-supervised Approach For Continual Noisy Label Learning [12.341250124228859]
  We propose a simple purification technique to effectively cleanse the online data stream that is both cost-effective and more accurate. After purification, we perform fine-tuning in a semi-supervised fashion that ensures the participation of all available samples. We achieve a 24.8% performance gain for CIFAR10 with 20% noise over previous SOTA methods.
  arXiv  Detail & Related papers  (2022-04-21T05:01:10Z)
• Class-Aware Contrastive Semi-Supervised Learning [51.205844705156046]
  We propose a general method named Class-aware Contrastive Semi-Supervised Learning (CCSSL) to improve pseudo-label quality and enhance the model's robustness in the real-world setting. Our proposed CCSSL has significant performance improvements over the state-of-the-art SSL methods on the standard datasets CIFAR100 and STL10.
  arXiv  Detail & Related papers  (2022-03-04T12:18:23Z)
• Robust Temporal Ensembling for Learning with Noisy Labels [0.0]
  We present robust temporal ensembling (RTE), which combines robust loss with semi-supervised regularization methods to achieve noise-robust learning. RTE achieves state-of-the-art performance across the CIFAR-10, CIFAR-100, ImageNet, WebVision, and Food-101N datasets.
  arXiv  Detail & Related papers  (2021-09-29T16:59:36Z)
• To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection [95.21700830273221]
  Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. We propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions. We prove that even a much smaller dataset with well-matched annotations can facilitate models to achieve better performance as well as generalizability.
  arXiv  Detail & Related papers  (2021-09-04T02:45:22Z)
• Augmentation Strategies for Learning with Noisy Labels [3.698228929379249]
  We evaluate different augmentation strategies for algorithms tackling the "learning with noisy labels" problem. We find that using one set of augmentations for loss modeling tasks and another set for learning is the most effective. We introduce this augmentation strategy to the state-of-the-art technique and demonstrate that we can improve performance across all evaluated noise levels.
  arXiv  Detail & Related papers  (2021-03-03T02:19:35Z)

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.