ChronoSelect: Robust Learning with Noisy Labels via Dynamics Temporal Memory

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Jianchao, Li, Qingfeng, Zheng, Pengcheng, Pu, Xiaorong, Ren, Yazhou
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908716402475008
author Wang, Jianchao
Li, Qingfeng
Zheng, Pengcheng
Pu, Xiaorong
Ren, Yazhou
author_facet Wang, Jianchao
Li, Qingfeng
Zheng, Pengcheng
Pu, Xiaorong
Ren, Yazhou
contents Training deep neural networks on real-world datasets is often hampered by the presence of noisy labels, which can be memorized by over-parameterized models, leading to significant degradation in generalization performance. While existing methods for learning with noisy labels (LNL) have made considerable progress, they fundamentally suffer from static snapshot evaluations and fail to leverage the rich temporal dynamics of learning evolution. In this paper, we propose ChronoSelect (chrono denoting its temporal nature), a novel framework featuring an innovative four-stage memory architecture that compresses prediction history into compact temporal distributions. Our unique sliding update mechanism with controlled decay maintains only four dynamic memory units per sample, progressively emphasizing recent patterns while retaining essential historical knowledge. This enables precise three-way sample partitioning into clean, boundary, and noisy subsets through temporal trajectory analysis and dual-branch consistency. Theoretical guarantees prove the mechanism's convergence and stability under noisy conditions. Extensive experiments demonstrate ChronoSelect's state-of-the-art performance across synthetic and real-world benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18183
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ChronoSelect: Robust Learning with Noisy Labels via Dynamics Temporal Memory
Wang, Jianchao
Li, Qingfeng
Zheng, Pengcheng
Pu, Xiaorong
Ren, Yazhou
Machine Learning
Computer Vision and Pattern Recognition
Training deep neural networks on real-world datasets is often hampered by the presence of noisy labels, which can be memorized by over-parameterized models, leading to significant degradation in generalization performance. While existing methods for learning with noisy labels (LNL) have made considerable progress, they fundamentally suffer from static snapshot evaluations and fail to leverage the rich temporal dynamics of learning evolution. In this paper, we propose ChronoSelect (chrono denoting its temporal nature), a novel framework featuring an innovative four-stage memory architecture that compresses prediction history into compact temporal distributions. Our unique sliding update mechanism with controlled decay maintains only four dynamic memory units per sample, progressively emphasizing recent patterns while retaining essential historical knowledge. This enables precise three-way sample partitioning into clean, boundary, and noisy subsets through temporal trajectory analysis and dual-branch consistency. Theoretical guarantees prove the mechanism's convergence and stability under noisy conditions. Extensive experiments demonstrate ChronoSelect's state-of-the-art performance across synthetic and real-world benchmarks.
title ChronoSelect: Robust Learning with Noisy Labels via Dynamics Temporal Memory
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.18183