xiaoboxia

T-Revision

NeurIPS'2019: Are Anchor Points Really Indispensable in Label-Noise Learning?

CDR

ICLR‘2021: Robust Early-learning: Hindering the Memorization of Noisy Labels

Part-dependent-label-noise

NeurIPS'2020: Part-dependent Label Noise: Towards Instance-dependent Label Noise

Classification-with-noisy-labels-by-importance-reweighting

TPAMI: Classification with noisy labels by importance reweighting.

PICMM

NeurIPS'2022: Pluralistic Image Completion with Gaussian Mixture Models

RTM_LNL

Regularly Truncated M-estimators for Learning with Noisy Labels

CoDis

ICCV'2023: Combating Noisy Labels with Sample Selection by Mining High-Discrepancy Examples

HLC

ICCV'2023: Holistic Label Correction for Noisy Multi-Label Classification

CNLCU

TML-Group

The code that TML group often uses

rethinking-network-pruning

Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)

pytorch-sigua

Pytorch implemetations of SIGUA

LBCS

ICML'2024: Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints

Sel-CL

Class2Simi

ICML‘2021: Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels

Co-teaching

NeurIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels

Moderate-DS

Advances-in-Label-Noise-Learning

A curated (most recent) list of resources for Learning with Noisy Labels

FLAML

A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.

HumanMAC

Official code for "HumanMAC: Masked Motion Completion for Human Motion Prediction".

IDEAL

Neural-PDE-Solver

xiaoboxia.github.io

Homepage