28 Open source projects that are alternatives of or similar to Active-Passive-Losses

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

AAAI 2021: Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise

Official Pytorch implementation of ReBias (Learning De-biased Representations with Biased Representations), ICML 2020

Official PyTorch implementation of Time-aware Large Kernel (TaLK) Convolutions (ICML 2020)

ICML 2019: Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels

Code for reproducing results in ICML 2020 paper "PackIt: A Virtual Environment for Geometric Planning"

Official code for UnICORNN (ICML 2021)

Implementation of ICML'2021:Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces

Code for "Distributed, Egocentric Representations of Graphs for Detecting Critical Structures" (ICML 2019)

Complete download for papers in various top conferences

FedScale is a scalable and extensible open-source federated learning (FL) platform.

Keras implementation of Training Deep Neural Networks on Noisy Labels with Bootstrapping, Reed et al. 2015

Code for our paper, Neural Network Attributions: A Causal Perspective (ICML 2019).

Papers, authors and author affiliations from ICML, NeurIPS and ICLR 2006-2021

WRENCH: Weak supeRvision bENCHmark

Tensorflow source code for "CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise" (CVPR 2018)

PyTorch implementation of "Contrast to Divide: self-supervised pre-training for learning with noisy labels"

Papers with code. Sorted by stars. Updated weekly.

This repository contains all the papers accepted in top conference of computer vision, with convenience to search related papers.

This is a collection of papers and other resources related to fairness.

[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression

Code for the paper Semi-Conditional Normalizing Flows for Semi-Supervised Learning

NeuroAI-UW seminar, a regular weekly seminar for the UW community, organized by NeuroAI Shlizerman Lab.

Code for ICML 2019 paper "Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering" [long-oral]

The standard package for machine learning with noisy labels, finding mislabeled data, and uncertainty quantification. Works with most datasets and models.

The FactorGraph package provides the set of different functions to perform inference over the factor graph with continuous or discrete random variables using the belief propagation algorithm.

NLNL: Negative Learning for Noisy Labels

noisy labels; missing labels; semi-supervised learning; entropy; uncertainty; robustness and generalisation.