Label smoothed Aggregation cross entropy loss for generalisation in sequence to sequence tasks.
-
Updated
Dec 17, 2019 - Python
Label smoothed Aggregation cross entropy loss for generalisation in sequence to sequence tasks.
An implementation of MobileNetV3 with pyTorch
Soft Target and Label Smoothing in Text Classification for Probability Calibration of Output Distributions.
Label Smoothing applied in Focal Loss
label smoothing PyTorch implementation
📦Simple Tool Box with Pytorch
Implementations of different loss-correction techniques to help deep models learn under class-conditional label noise.
deep-learning image classification resnet50
Source code of our paper "Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation" @acl-2022
A simple template for classifying things
[ICML2022 Long Talk] Official Pytorch implementation of "To Smooth or Not? When Label Smoothing Meets Noisy Labels"
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
Code of our method MbLS (Margin-based Label Smoothing) for network calibration. To Appear at CVPR 2022. Paper : https://arxiv.org/abs/2111.15430
[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.
Knowledge Distillation: CVPR2020 Oral, Revisiting Knowledge Distillation via Label Smoothing Regularization
Supplementary material and code for "From Label Smoothing to Label Relaxation" as published at AAAI 2021.
Modern Eager TensorFlow implementation of Attention Is All You Need
Mean Teacher-based Cross-Domain Activity Recognition using WiFi Signals, IoTJ 2023
Code for "Memorization-Dilation: Modeling Neural Collapse under Noise" as published at ICLR 2023.
Adding Image-context in the Label Smoothing process via Geodesic distance
Add a description, image, and links to the label-smoothing topic page so that developers can more easily learn about it.
To associate your repository with the label-smoothing topic, visit your repo's landing page and select "manage topics."