paper-with-me

Papers

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 distribution. Label smoothing smoothes target labels with a predefined prior label distribution; as a result, a model is learned to maximize the likelihood of predicting the soft label. Nonetheless, the amount of smoothing is the same in all samples and remains fixed in training. In other words, label smoothing does not reflect the change in probability distribution mapped by a model over the course of training. To address this issue, we propose a regularization scheme that brings dynamic nature into the smoothing parameter by taking model probability distribution into account, thereby varying the parameter per instance. A model in training self-regulates the extent of smoothing on the fly during forward propagation. Furthermore, inspired by recent work in bridging label smoothing and knowledge distillation, our work utilizes self-knowledge as a prior label distribution in softening target labels, and presents theoretical support for the regularization effect by knowledge distillation. Our regularizer is validated comprehensively on various datasets in machine translation and outperforms strong baselines not only in model performance but also in model calibration by a large margin.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationMachine Translation

Methods 이 논문이 사용한 방법론

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

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

Double Reverse Regularization Network Based on Self-Knowledge Distillation for SAR Object Classification

2023-11-26 · Bo Xu, Hao Zheng, Zhigang Hu, Liu Yang 외

In current synthetic aperture radar (SAR) object classification, one of the major challenges is the severe overfitting issue due to the limited dataset (few-shot) and noisy data. Considering the advantages of knowledge d…

Knowledge DistillationSelf-Knowledge Distillation

Pseudo Knowledge Distillation: Towards Learning Optimal Instance-specific Label Smoothing Regularization

2021-09-29 · Peng Lu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh 외

Knowledge Distillation (KD) is an algorithm that transfers the knowledge of a trained, typically larger, neural network into another model under training. Although a complete understanding of KD is elusive, a growing bod…

image-classificationImage ClassificationKnowledge DistillationNatural Language Understanding

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

Variational Learning Induces Adaptive Label Smoothing

2025-02-11 · Sin-Han Yang, Zhedong Liu, Gian Maria Marconi, Mohammad Emtiyaz Khan

We show that variational learning naturally induces an adaptive label smoothing where label noise is specialized for each example. Such label-smoothing is useful to handle examples with labeling errors and distribution s…