Alternatives and similar repositories for early-exit-ensembles

Users that are interested in early-exit-ensembles are comparing it to the libraries listed below

• ondrejbohdal / meta-calibration
  Official PyTorch implementation of "Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error"
  ☆36Updated 2 years ago
• Nokia-Bell-Labs / kaizen
  (WACV'24) Kaizen: Practical self-supervised continual learning with continual fine-tuning
  ☆14Updated 10 months ago
• zhang64-llnl / Mix-n-Match-Calibration
  ☆38Updated 4 years ago
• aniruddhraghu / ecg_aug
  ☆16Updated 2 years ago
• TUM-DAML / dbu-robustness
  Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable ? (ICML 2021)
  ☆27Updated 2 years ago
• lunanbit / FedUL
  FedUL: Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
  ☆32Updated 2 years ago
• xxlya / Fed_ABIDE
  impelmentation of https://arxiv.org/pdf/2001.05647.pdf
  ☆37Updated 4 years ago
• sungyubkim / MCDO
  A pytorch implementation of MCDO(Monte-Carlo Dropout methods)
  ☆57Updated 6 years ago
• noowad93 / MIMO-pytorch
  PyTorch Implementation of MIMO (ICLR 2021)
  ☆16Updated 2 years ago
• cambridge-mlg / CLUE
  Code for the paper "Getting a CLUE: A Method for Explaining Uncertainty Estimates"
  ☆36Updated last year
• mlaves / well-calibrated-regression-uncertainty
  Code for our MIDL2020 submission "Well-Calibrated Regression Uncertainty in Medical Imaging with Deep Learning".
  ☆31Updated 4 years ago
• geifmany / uncertainty_ICLR
  Code for the paper "Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers" published in ICLR 2019
  ☆14Updated 6 years ago
• atilberk / evidential-deep-learning-to-quantify-classification-uncertainty
  Work on Evidential Deep Learning to Quantify Classification Uncertainty
  ☆60Updated 6 years ago
• samuelstanton / gnosis
  Code to reproduce experiments from 'Does Knowledge Distillation Really Work' a paper which appeared in the 2021 NeurIPS proceedings.
  ☆33Updated last year
• belaalb / G2DM
  Generalizing to unseen domains via distribution matching
  ☆72Updated 5 years ago
• wyf0912 / MIXALL
  [ICASSP 2020] Code release of paper 'Heterogeneous Domain Generalization via Domain Mixup'
  ☆26Updated 5 years ago
• junjieliu2910 / DynamicSparseTraining
  [ICLR-2020] Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers.
  ☆31Updated 5 years ago
• CityU-AIM-Group / PRR-FL
  [MICCAI'21] Personalized Retrogress-Resilient Framework for Real-World Medical Federated Learning
  ☆17Updated 3 years ago
• alshedivat / fedpa
  Federated posterior averaging implemented in JAX
  ☆51Updated 2 years ago
• Johswald / learning_where_to_learn
  ☆38Updated 9 months ago
• arobey1 / mbdg
  ☆36Updated 4 years ago
• mil-ad / prospr
  Prospect Pruning: Finding Trainable Weights at Initialization Using Meta-Gradients
  ☆32Updated 3 years ago
• Liuhong99 / Imbalanced-SSL
  Code Release for "Self-supervised Learning is More Robust to Dataset Imbalance"
  ☆39Updated 3 years ago
• sharpenb / Posterior-Network
  Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts (Neurips 2020)
  ☆78Updated 3 years ago
• alexrame / fishr
  Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization
  ☆87Updated 3 years ago
• IntelLabs / AVUC
  Code to accompany the paper 'Improving model calibration with accuracy versus uncertainty optimization'.
  ☆54Updated 2 years ago
• VirtuosoResearch / Regularized-Self-Labeling
  A regularized self-labeling approach to improve the generalization and robustness of fine-tuned models
  ☆27Updated 3 years ago
• KaosEngineer / PriorNetworks
  ☆66Updated 5 years ago
• mominabbass / Sharp-MAML
  Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning
  ☆32Updated 2 years ago
• singlasahil14 / SOC
  Code for the ICML 2021 and ICLR 2022 papers: Skew Orthogonal Convolutions, Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100
  ☆18Updated 3 years ago