SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.06930 · CVPR · 2023

Twin Contrastive Learning with Noisy Labels

Junping Zhang, Hongming Shan, Zhizhong Huang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Learning from noisy data is a challenging task that significantly degenerates the model performance. In this paper, we present TCL, a novel twin contrastive learning model to learn robust representations and handle noisy labels for classification. Specifically, we construct a Gaussian mixture model (GMM) over the representations by injecting the supervised model predictions into GMM to link labelfree latent variables in GMM with label-noisy annotations. Then, TCL detects the examples with wrong labels as the outof-distribution examples by another two-component GMM, taking into account the data distribution. We further propose a cross-supervision with an entropy regularization loss that bootstraps the true targets from model predictions to handle the noisy labels. As a result, TCL can learn discriminative representations aligned with estimated labels through mixup and contrastive learning. Extensive experimental results on several standard benchmarks and real-world datasets demonstrate the superior performance of TCL. In particular, TCL achieves 7.5% improvements on CIFAR-10 with 90% noisy label-an extremely noisy scenario. The source code is available at https://github.com/Hzzone/TCL.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.06930")
get_code_for_paper("2303.06930")
have("2303.06930")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.06930.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.06930.svg)](https://syntology.ai/paper/2303.06930)

Connect an agent — have() is free.