evidential-deep-learning 开源项目推荐（25 个）

dougbrion /pytorch-classification-uncertainty

This repo contains a PyTorch implementation of the paper: "Evidential Deep Learning to Quantify Classification Uncertainty"

MengyuanChen21 /Awesome-Evidential-Deep-Learning

A curated publication list on evidential deep learning.

aamini /chemprop

Fast and scalable uncertainty quantification for neural molecular property prediction, accelerated optimization, and guided virtual screening.

Cogito2012 /DEAR

[ICCV 2021 Oral] Deep Evidential Action Recognition

MengyuanChen21 /ICLR2024-REDL

[ICLR 2024 Spotlight] R-EDL: Relaxing Nonessential Settings of Evidential Deep Learning

MengyuanChen21 /ECCV2022-DELU

[ECCV 2022] Dual-Evidential Learning for Weakly-supervised Temporal Action Localization

clabrugere /evidential-deeplearning

Implementation of "Evidential Deep Learning to Quantify Classification Uncertainty" proposing a method to quantify uncertainty in a neural network.

ai2es /miles-guess

Machine learning models for estimating aleatoric and epistemic uncertainty with evidential and ensemble methods.

MengyuanChen21 /Re-EDL

[TPAMI 2025] Revisiting Essential and Non-Essential Settings of Evidential Deep Learning

lijun2005 /ICML26-Holmes

[ICML 2026] Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval

obiyoag /evi-CEM

Official implementation of MICCAI2024 paper "Evidential Concept Embedding Models: Towards Reliable Concept Explanations for Skin Disease Diagnosis"

deargen /MT-ENet

Repository for "Improving evidential deep learning via multi-task learning," published in AAAI2022

sandylaker /ib-edl

Calibrating LLMs with Information-Theoretic Evidential Deep Learning (ICLR 2025)

maohaos2 /EDL-Mirage

[NeurIPS 2024] Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?

Liangyu-Xiang /EKD

Official Implementation of Evidential Knowledge Distillation (ICCV 2025)

DoktorMike /EvidentialFlux.jl

Evidential Deep Learning Layers for Flux

CDDLeiden /uqdd

Hybrid Uncertainty Quantification for Bioactivity Assessment

team-daniel /cedl

Our Conflict-aware Evidential Deep Learning (C-EDL) method enhances robustness to OOD and adversarial inputs by combining evidence from metamorphic transformations and reducing evidence when conflicts arise, signalling higher uncertainty.

royxforge /unsupervised-confidence-estimation

Label-free confidence estimation for neural networks - benchmarking MSP, MC Dropout, EDL, and Deep Ensembles with a novel unsupervised uncertainty metric.

NikaNats /cxr-multilabel-classification

Multi-label Chest X-ray classification on ChestMNIST using LISA (Language-Invariant Semantic Anchoring) and PaQ (Pathology-as-Query) with conformal safety guarantees, evidential deep learning, and post-hoc calibration.