Delving Deep into Label Smoothing

• URL: http://arxiv.org/abs/2011.12562v2
• Date: Thu, 22 Jul 2021 08:32:54 GMT
• Title: Delving Deep into Label Smoothing
• Authors: Chang-Bin Zhang, Peng-Tao Jiang, Qibin Hou, Yunchao Wei, Qi Han, Zhen Li, Ming-Ming Cheng
• Abstract summary: 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.
• Score: 112.24527926373084
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Label smoothing is an effective regularization tool for deep neural networks (DNNs), which generates soft labels by applying a weighted average between the uniform distribution and the hard label. It is often used to reduce the overfitting problem of training DNNs and further improve classification performance. In this paper, we aim to investigate how to generate more reliable soft labels. We present an Online Label Smoothing (OLS) strategy, which generates soft labels based on the statistics of the model prediction for the target category. The proposed OLS constructs a more reasonable probability distribution between the target categories and non-target categories to supervise DNNs. Experiments demonstrate that based on the same classification models, the proposed approach can effectively improve the classification performance on CIFAR-100, ImageNet, and fine-grained datasets. Additionally, the proposed method can significantly improve the robustness of DNN models to noisy labels compared to current label smoothing approaches.

Related papers

• Improving Time Series Classification with Representation Soft Label Smoothing [3.3470010424473036]
  Previous research has indicated that deep neural network based models for time series classification (TSC) tasks are prone to overfitting. We propose a novel approach to generate more reliable soft labels, which we refer to as representation soft label smoothing. Our method demonstrates strong performance across models with varying structures and complexities.
  arXiv  Detail & Related papers  (2024-08-30T04:50:27Z)
• An Embedding is Worth a Thousand Noisy Labels [0.11999555634662634]
  We propose WANN, a weighted Adaptive Nearest Neighbor approach to address label noise. We show WANN outperforms reference methods on diverse datasets of varying size and under various noise types and severities. Our approach, emphasizing efficiency and explainability, emerges as a simple, robust solution to overcome the inherent limitations of deep neural network training.
  arXiv  Detail & Related papers  (2024-08-26T15:32:31Z)
• Posterior Label Smoothing for Node Classification [2.737276507021477]
  We propose a simple yet effective label smoothing for the transductive node classification task. We design the soft label to encapsulate the local context of the target node through the neighborhood label distribution. In the following analysis, we find that incorporating global label statistics in posterior computation is the key to the success of label smoothing.
  arXiv  Detail & Related papers  (2024-06-01T11:59:49Z)
• Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification [49.09505771145326]
  We propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
  arXiv  Detail & Related papers  (2024-04-26T06:00:27Z)
• RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Inter-label Correlations [52.549807652527306]
  This paper introduces RankMatch, an innovative approach for Semi-Supervised Label Distribution Learning (SSLDL) RankMatch effectively utilizes a small number of labeled examples in conjunction with a larger quantity of unlabeled data. We establish a theoretical generalization bound for RankMatch, and through extensive experiments, demonstrate its superiority in performance against existing SSLDL methods.
  arXiv  Detail & Related papers  (2023-12-11T12:47:29Z)
• Balancing Efficiency vs. Effectiveness and Providing Missing Label Robustness in Multi-Label Stream Classification [3.97048491084787]
  We propose a neural network-based approach to high-dimensional multi-label classification. Our model uses a selective concept drift adaptation mechanism that makes it suitable for a non-stationary environment. We adapt our model to an environment with missing labels using a simple yet effective imputation strategy.
  arXiv  Detail & Related papers  (2023-10-01T13:23:37Z)
• All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation [67.30502812804271]
  Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning. We propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions.
  arXiv  Detail & Related papers  (2023-05-25T08:19:31Z)
• Transductive CLIP with Class-Conditional Contrastive Learning [68.51078382124331]
  We propose Transductive CLIP, a novel framework for learning a classification network with noisy labels from scratch. A class-conditional contrastive learning mechanism is proposed to mitigate the reliance on pseudo labels. ensemble labels is adopted as a pseudo label updating strategy to stabilize the training of deep neural networks with noisy labels.
  arXiv  Detail & Related papers  (2022-06-13T14:04:57Z)
• Unified Robust Training for Graph NeuralNetworks against Label Noise [12.014301020294154]
  We propose a new framework, UnionNET, for learning with noisy labels on graphs under a semi-supervised setting. Our approach provides a unified solution for robustly training GNNs and performing label correction simultaneously.
  arXiv  Detail & Related papers  (2021-03-05T01:17:04Z)
• PseudoSeg: Designing Pseudo Labels for Semantic Segmentation [78.35515004654553]
  We present a re-design of pseudo-labeling to generate structured pseudo labels for training with unlabeled or weakly-labeled data. We demonstrate the effectiveness of the proposed pseudo-labeling strategy in both low-data and high-data regimes.
  arXiv  Detail & Related papers  (2020-10-19T17:59:30Z)

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.