• Home
  • Search
  • MixNN: Combating Noisy Labels in Deep Learning by Mixing with Nearest Neighbors
  • https://doi.org/10.1109/bigdata52589.2021.9671816Copy DOI Icon

MixNN: Combating Noisy Labels in Deep Learning by Mixing with Nearest Neighbors

  • Dec 15, 2021
  • Yangdi Lu +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Noisy labels are ubiquitous in real-world datasets, especially in the ones from web sources. Training deep neural networks on noisy datasets is a challenging task, as the networks have been shown to overfit the noisy labels in training, resulting in performance degradation. When trained on noisy datasets, deep neural networks have been observed to fit t he clean samples during an "early learning" phase, before eventually memorizing the mislabeled samples. We further explore the representation distributions in the early learning stage and find that the representations of similar samples from the same classes congregate regardless of their noisy labels. Inspired by these findings, we propose MixNN, a novel framework to mitigate the influence of noisy labels. In contrast with existing methods, which identify and eliminate the mislabeled samples, we modify the mislabeled samples by mixing them with their nearest neighbors through a weighted sum approach. The weights are calculated with a mixture model learning from the sample loss distribution. To enhance the performance in the presence of extreme label noise, we propose a strategy to estimate the soft targets by gradually correcting the noisy labels. We demonstrate that the estimated targets yield a more accurate approximation to ground truth labels and a better quality of the learned representations with more separated and clearly bounded clusters. Extensive experiments in two benchmarks and two challenging real-world datasets demonstrate that our approach outperforms the existing state-of-the-art methods.

Similar Papers
  • Research Article
  • Citations2

Mutual calibration training: Training deep neural networks with noisy labels using dual-models

  • Sep 13, 2021
  • Computer Vision and Image Understanding
  • Rui Liu +3
  • Research Article
  • Citations8

Class-Independent Regularization for Learning with Noisy Labels

  • Jun 26, 2023
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Rumeng Yi +3
  • Conference Article
  • Citations2

Identifying the Training Stop Point with Noisy Labeled Data

  • Dec 01, 2020
  • Sree Ram Kamabattula +3
  • Research Article
  • Citations4

Agree to Disagree: Robust Anomaly Detection with Noisy Labels

  • Feb 10, 2025
  • Proceedings of the ACM on Management of Data
  • Dennis M Hofmann +6
  • PDF
  • Research Article
  • Citations4

CRAS: Curriculum Regularization and Adaptive Semi-Supervised Learning with Noisy Labels

  • Jan 31, 2024
  • Applied Sciences
  • Ryota Higashimoto +2
  • Research Article
  • Citations16

Skin Lesion Segmentation in Dermoscopic Images with Noisy Data.

  • Apr 05, 2023
  • Journal of digital imaging
  • Norsang Lama +4
  • Book Chapter
  • Citations3

Robust Training of Deep Neural Networks with Noisy Labels by Graph Label Propagation

  • Jan 01, 2021
  • Yuichiro Nomura +1
  • Conference Article
  • Citations2

Analyzing Deep Neural Networks with Noisy Labels

  • Feb 01, 2020
  • Chan Lim +2
  • Research Article

Outlier-trimmed dual-interval smoothing loss for sample selection in learning with noisy labels.

  • Nov 01, 2025
  • Neural networks : the official journal of the International Neural Network Society
  • Senyu Hou +4
  • Research Article
  • Citations11

Learning with noisy labels using collaborative sample selection and contrastive semi-supervised learning

  • Apr 27, 2024
  • Knowledge-Based Systems
  • Qing Miao +6
  • Conference Article
  • Citations378

Iterative Learning with Open-set Noisy Labels

  • Jun 01, 2018
  • Yisen Wang +6
  • Research Article
  • Citations179

Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges

  • May 04, 2021
  • IEEE Transactions on Artificial Intelligence
  • Edgar Galván +1
  • Conference Article
  • Citations2

Teacher/Student Deep Semi-Supervised Learning for Training with Noisy Labels

  • Dec 01, 2018
  • Zeyad Hailat +1
  • Research Article
  • Citations5

Training deep neural networks with noisy clinical labels: toward accurate detection of prostate cancer in US data.

  • Jul 26, 2022
  • International Journal of Computer Assisted Radiology and Surgery
  • Golara Javadi +9
  • Research Article
  • Citations27

An joint end-to-end framework for learning with noisy labels

  • Apr 22, 2021
  • Applied Soft Computing
  • Qian Zhang +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.