REsponsible & Accountable Learning (REAL)
@ University of California, Santa Cruz

1st Learning and Mining with Noisy Labels Challenge

IJCAI-ECAI 2022

The first Learning and Mining with Noisy Labels Challenge is a part of IJCAI-ECAI 2022. The dataset is CIFAR-N, a recently collected human-annotations for CIFAR. The goal of the challenge is to prepare the community shift from synthetic label noise benchmarks to tasks with real human-annotated data. Unlike the webvision challenge, CIFAR-N is small in size, containing a set of easily accessible, easy-to-use, and verifiable datasets, making training and evaluating CIFAR-N very resource-friendly. 
This year, we organize two tasks to evaluate the learned knowledge and representation on CIFAR-N:  
(1) Image Classification Task.
(2) Label Noise Detection Task.

Task 1
Image Classification
Task 2 
Label Noise Detection

Timelines

Organizers and Committees

Yang Liu

Assistant Professor
Director of REAL Lab 
University of California 
Santa Cruz

Tongliang Liu

Director of Sydney AI Centre
Director of TML Lab
University of Sydney

Gang Niu

Research Scientist
RIKEN AIP
Adjunct Professor
Southeast University

Chen Gong

Professor
Nanjing University of Science and Technology

Bo Han

Assistant Professor
Hong Kong Baptist University
Visiting Scientist
RIKEN AIP

Jiaheng Wei

Student Organizer
PhD Candidate
University of California 
Santa Cruz

Zhaowei Zhu

Student Organizer
PhD Candidate
University of California 
Santa Cruz

Hao Cheng

Student Organizer
PhD Student
University of California 
Santa Cruz

 Call for Participants  Call for program committees

Click the above red button to complete a preliminary survey regarding your preferences for participatation

Click the above red button to complete a preliminary survey regarding your preferences for servering as a PC.

Sponsor

Snorkel AI

Unlock the true potential of machine learning by removing the bottleneck of hand-labeled training data with Snorkel Flow.

Amber Group

A team of 1000+ dynamic, entrepreneurial technologists, traders, and engineers on a mission to create frictionless marketplaces.

Prizes

If you have further questions about the challenge, please contact us via lmnl.challenge@gmail.com.