KNN-enhanced Deep Learning Against Noisy Labels

• URL: http://arxiv.org/abs/2012.04224v1
• Date: Tue, 8 Dec 2020 05:21:29 GMT
• Title: KNN-enhanced Deep Learning Against Noisy Labels
• Authors: Shuyu Kong and You Li and Jia Wang and Amin Rezaei and Hai Zhou
• Abstract summary: Supervised learning on Deep Neural Networks (DNNs) is data hungry. In this work, we propose to apply deep KNN for label cleanup. We iteratively train the neural network and update labels to simultaneously proceed towards higher label recovery rate and better classification performance.
• Score: 4.765948508271371
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Supervised learning on Deep Neural Networks (DNNs) is data hungry. Optimizing performance of DNN in the presence of noisy labels has become of paramount importance since collecting a large dataset will usually bring in noisy labels. Inspired by the robustness of K-Nearest Neighbors (KNN) against data noise, in this work, we propose to apply deep KNN for label cleanup. Our approach leverages DNNs for feature extraction and KNN for ground-truth label inference. We iteratively train the neural network and update labels to simultaneously proceed towards higher label recovery rate and better classification performance. Experiment results show that under the same setting, our approach outperforms existing label correction methods and achieves better accuracy on multiple datasets, e.g.,76.78% on Clothing1M dataset.

Related papers

• KD-FixMatch: Knowledge Distillation Siamese Neural Networks [13.678635878305247]
  KD-FixMatch is a novel SSL algorithm that addresses the limitations of FixMatch by incorporating knowledge distillation. The algorithm utilizes a combination of sequential and simultaneous training of SNNs to enhance performance and reduce performance degradation. Our results indicate that KD-FixMatch has a better training starting point that leads to improved model performance compared to FixMatch.
  arXiv  Detail & Related papers  (2023-09-11T21:11:48Z)
• Robust Training of Graph Neural Networks via Noise Governance [27.767913371777247]
  Graph Neural Networks (GNNs) have become widely-used models for semi-supervised learning. In this paper, we consider an important yet challenging scenario where labels on nodes of graphs are not only noisy but also scarce. We propose a novel RTGNN framework that achieves better robustness by learning to explicitly govern label noise.
  arXiv  Detail & Related papers  (2022-11-12T09:25:32Z)
• Understanding and Improving Early Stopping for Learning with Noisy Labels [63.0730063791198]
  The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-the-art label-noise learning methods. Current methods generally decide the early stopping point by considering a DNN as a whole. We propose to separate a DNN into different parts and progressively train them to address this problem.
  arXiv  Detail & Related papers  (2021-06-30T07:18:00Z)
• INN: A Method Identifying Clean-annotated Samples via Consistency Effect in Deep Neural Networks [1.1470070927586016]
  We introduce a new method called INN to refine clean labeled data from training data with noisy labels. The INN method requires more computation but is much stable and powerful than the small-loss strategy.
  arXiv  Detail & Related papers  (2021-06-29T09:06:21Z)
• NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs [20.470934944907608]
  Graph Neural Networks (GNNs) have achieved promising results for semi-supervised learning tasks on graphs such as node classification. Many real-world graphs are often sparsely and noisily labeled, which could significantly degrade the performance of GNNs. We propose to develop a label noise-resistant GNN for semi-supervised node classification.
  arXiv  Detail & Related papers  (2021-06-08T22:12:44Z)
• Adaptive Nearest Neighbor Machine Translation [60.97183408140499]
  kNN-MT combines pre-trained neural machine translation with token-level k-nearest-neighbor retrieval. Traditional kNN algorithm simply retrieves a same number of nearest neighbors for each target token. We propose Adaptive kNN-MT to dynamically determine the number of k for each target token.
  arXiv  Detail & Related papers  (2021-05-27T09:27:42Z)
• Boosting Semi-Supervised Face Recognition with Noise Robustness [54.342992887966616]
  This paper presents an effective solution to semi-supervised face recognition that is robust to the label noise aroused by the auto-labelling. We develop a semi-supervised face recognition solution, named Noise Robust Learning-Labelling (NRoLL), which is based on the robust training ability empowered by GN.
  arXiv  Detail & Related papers  (2021-05-10T14:43:11Z)
• Delving Deep into Label Smoothing [112.24527926373084]
  Label smoothing is an effective regularization tool for deep neural networks (DNNs) We present an Online Label Smoothing (OLS) strategy, which generates soft labels based on the statistics of the model prediction for the target category.
  arXiv  Detail & Related papers  (2020-11-25T08:03:11Z)
• Temporal Calibrated Regularization for Robust Noisy Label Learning [60.90967240168525]
  Deep neural networks (DNNs) exhibit great success on many tasks with the help of large-scale well annotated datasets. However, labeling large-scale data can be very costly and error-prone so that it is difficult to guarantee the annotation quality. We propose a Temporal Calibrated Regularization (TCR) in which we utilize the original labels and the predictions in the previous epoch together.
  arXiv  Detail & Related papers  (2020-07-01T04:48:49Z)
• COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization [60.07531696857743]
  Co-Learns DNNs and soft labels through Alternating Minimization of two objectives. We propose COLAM framework that Co-Learns DNNs and soft labels through Alternating Minimization of two objectives.
  arXiv  Detail & Related papers  (2020-04-26T17:50:20Z)

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.