paper-with-me

홈 › Papers

Regularization via Adaptive Pairwise Label Smoothing

2020-12-02 · Hongyu Guo

Label Smoothing (LS) is an effective regularizer to improve the generalization of state-of-the-art deep models. For each training sample the LS strategy smooths the one-hot encoded training signal by distributing its distribution mass over the non ground-truth classes, aiming to penalize the networks from generating overconfident output distributions. This paper introduces a novel label smoothing technique called Pairwise Label Smoothing (PLS). The PLS takes a pair of samples as input. Smoothing with a pair of ground-truth labels enables the PLS to preserve the relative distance between the two truth labels while further soften that between the truth labels and the other targets, resulting in models producing much less confident predictions than the LS strategy. Also, unlike current LS methods, which typically require to find a global smoothing distribution mass through cross-validation search, PLS automatically learns the distribution mass for each input pair during training. We empirically show that PLS significantly outperforms LS and the baseline models, achieving up to 30% of relative classification error reduction. We also visually show that when achieving such accuracy gains the PLS tends to produce very low winning softmax scores.

📄 PDF Abstract BibTeX arXiv:2012.01559

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Combined Image Data Augmentations diminish the benefits of Adaptive Label Smoothing

2025-07-22 · Georg Siedel, Ekagra Gupta, Weijia Shao, Silvia Vock 외 arxiv

Soft augmentation regularizes the supervised learning process of image classifiers by reducing label confidence of a training sample based on the magnitude of random-crop augmentation applied to it. This paper extends th…

Data Augmentation

Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation

2022-10-22 · Dongkyu Lee, Ka Chun Cheung, Nevin L. Zhang

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked d…

Knowledge DistillationText Generation

Adaptive Label Smoothing with Self-Knowledge

2021-09-29 · Dongkyu Lee, Ka Chun Cheung, Nevin Zhang

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked d…

Knowledge DistillationMachine Translation

A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise

2022-06-15 · Jongwoo Ko, Bongsoo Yi, Se-Young Yun

As deep neural networks can easily overfit noisy labels, robust training in the presence of noisy labels is becoming an important challenge in modern deep learning. While existing methods address this problem in various …

Adaptive Regularization of Labels

2019-08-15 · Qianggang Ding, Sifan Wu, Hao Sun, Jiadong Guo 외

Recently, a variety of regularization techniques have been widely applied in deep neural networks, such as dropout, batch normalization, data augmentation, and so on. These methods mainly focus on the regularization of w…

Data AugmentationKnowledge Distillationtext-classificationText Classification