There are 2 repositories under label-smoothing topic.
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
利用pytorch实现图像分类的一个完整的代码,训练,预测,TTA,模型融合,模型部署,cnn提取特征,svm或者随机森林等进行分类,模型蒸馏,一个完整的代码
Knowledge Distillation: CVPR2020 Oral, Revisiting Knowledge Distillation via Label Smoothing Regularization
[ICML2022 Long Talk] Official Pytorch implementation of "To Smooth or Not? When Label Smoothing Meets Noisy Labels"
An implementation of MobileNetV3 with pyTorch
label smoothing PyTorch implementation
Source code of our paper "Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation" @ACL-2022
Supplementary material and code for "From Label Smoothing to Label Relaxation" as published at AAAI 2021.
Label smoothed Aggregation cross entropy loss for generalisation in sequence to sequence tasks.
Label Smoothing applied in Focal Loss
Mean Teacher-based Cross-Domain Activity Recognition using WiFi Signals, IoTJ 2023
[ICML 2022] This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). We suggest to use an LS-trained teacher with a low-temperature transfer to render high performance students.
:package:Simple Tool Box with Pytorch
Build an algorithm that can predict multiple future states of Limit Order Books using high-frequency, multi-variate, short time-frame data
Soft Target and Label Smoothing in Text Classification for Probability Calibration of Output Distributions.
Building High Performance Convolutional Neural Networks with TensorFlow
A simple template for classifying things
Modern Eager TensorFlow implementation of Attention Is All You Need
Multiple Generation Based Knowledge Distillation: A Roadmap
Label Smoothing and Adversarial Robustness
Code for "Memorization-Dilation: Modeling Neural Collapse under Noise" as published at ICLR 2023.
Anime Face Generation using GANS and Label Smoothing.
Implementations of different loss-correction techniques to help deep models learn under class-conditional label noise.
deep-learning image classification resnet50