SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.14932 · 2021

Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection

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

Recent studies on learning with noisy labels have shown remarkable performance by exploiting a small clean dataset. In particular, model agnostic meta-learning-based label correction methods further improve performance by correcting noisy labels on the fly. However, there is no safeguard on the label miscorrection, resulting in unavoidable performance degradation. Moreover, every training step requires at least three back-propagations, significantly slowing down the training speed. To mitigate these issues, we propose a robust and efficient method that learns a label transition matrix on the fly. Employing the transition matrix makes the classifier skeptical about all the corrected samples, which alleviates the miscorrection issue. We also introduce a two-head architecture to efficiently estimate the label transition matrix every iteration within a single back-propagation, so that the estimated matrix closely follows the shifting noise distribution induced by label correction. Extensive experiments demonstrate that our approach shows the best performance in training efficiency while having comparable or better accuracy than existing methods.

For agents

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

get_harvested_code_for_paper("2111.14932")
get_code_for_paper("2111.14932")
have("2111.14932")

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

curl https://syntology.ai/api/ran/2111.14932.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.14932.svg)](https://syntology.ai/paper/2111.14932)

Connect an agent — have() is free.