Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Label-smoothing-Selective-classification – AI Model by ENSTA-U2IS | AlphaNeural AI
You can deploy this model and start earning money today!
ENSTA-U2IS
/
Label-smoothing-Selective-classification
like
0
uncertainty quantification
model robustness
selective classification
label-smoothing
ILSVRC/imagenet-1k
2403.14715
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
arXiv
This repository contains the models trained as experimental support for the paper "Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It" published at ICLR 2025.
The code is based on
TorchUncertainty
and available on
GitHub
.
List of models
This repository contains:
for classification on ImageNet with ViTs: 4 ViTs-S/16 trained with label-smoothing coefficients in [0, 0.1, 0.2, 0.3]
for classification on ImageNet with ResNets: 4 ResNet-50 trained with label-smoothing coefficients in [0, 0.1, 0.2, 0.3]
for classification on CIFAR-100: 4 DenseNet-BC trained with label-smoothing coefficients in [0, 0.1, 0.2, 0.3]
for segmentation: 4 DeepLabv3+ Resnet-101 trained with label-smoothing coefficients in [0, 0.1, 0.2, 0.3]
for nlp: one CE-based and one LS-based (LS coefficient 0.6) LSTM-MLP
The rest of the models (notably on tabular data) used in the paper are trainable on CPU in the dedicated notebooks.
