AEON: Adaptive Estimation of Instance-Dependent In-Distribution and Out-of-Distribution Label Noise for Robust Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Garg, Arpit, Nguyen, Cuong, Felix, Rafael, Liu, Yuyuan, Do, Thanh-Toan, Carneiro, Gustavo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915117706248192
author Garg, Arpit
Nguyen, Cuong
Felix, Rafael
Liu, Yuyuan
Do, Thanh-Toan
Carneiro, Gustavo
author_facet Garg, Arpit
Nguyen, Cuong
Felix, Rafael
Liu, Yuyuan
Do, Thanh-Toan
Carneiro, Gustavo
contents Robust training with noisy labels is a critical challenge in image classification, offering the potential to reduce reliance on costly clean-label datasets. Real-world datasets often contain a mix of in-distribution (ID) and out-of-distribution (OOD) instance-dependent label noise, a challenge that is rarely addressed simultaneously by existing methods and is further compounded by the lack of comprehensive benchmarking datasets. Furthermore, even though current noisy-label learning approaches attempt to find noisy-label samples during training, these methods do not aim to estimate ID and OOD noise rates to promote their effectiveness in the selection of such noisy-label samples, and they are often represented by inefficient multi-stage learning algorithms. We propose the Adaptive Estimation of Instance-Dependent In-Distribution and Out-of-Distribution Label Noise (AEON) approach to address these research gaps. AEON is an efficient one-stage noisy-label learning methodology that dynamically estimates instance-dependent ID and OOD label noise rates to enhance robustness to complex noise settings. Additionally, we introduce a new benchmark reflecting real-world ID and OOD noise scenarios. Experiments demonstrate that AEON achieves state-of-the-art performance on both synthetic and real-world datasets
format Preprint
id arxiv_https___arxiv_org_abs_2501_13389
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AEON: Adaptive Estimation of Instance-Dependent In-Distribution and Out-of-Distribution Label Noise for Robust Learning
Garg, Arpit
Nguyen, Cuong
Felix, Rafael
Liu, Yuyuan
Do, Thanh-Toan
Carneiro, Gustavo
Computer Vision and Pattern Recognition
Robust training with noisy labels is a critical challenge in image classification, offering the potential to reduce reliance on costly clean-label datasets. Real-world datasets often contain a mix of in-distribution (ID) and out-of-distribution (OOD) instance-dependent label noise, a challenge that is rarely addressed simultaneously by existing methods and is further compounded by the lack of comprehensive benchmarking datasets. Furthermore, even though current noisy-label learning approaches attempt to find noisy-label samples during training, these methods do not aim to estimate ID and OOD noise rates to promote their effectiveness in the selection of such noisy-label samples, and they are often represented by inefficient multi-stage learning algorithms. We propose the Adaptive Estimation of Instance-Dependent In-Distribution and Out-of-Distribution Label Noise (AEON) approach to address these research gaps. AEON is an efficient one-stage noisy-label learning methodology that dynamically estimates instance-dependent ID and OOD label noise rates to enhance robustness to complex noise settings. Additionally, we introduce a new benchmark reflecting real-world ID and OOD noise scenarios. Experiments demonstrate that AEON achieves state-of-the-art performance on both synthetic and real-world datasets
title AEON: Adaptive Estimation of Instance-Dependent In-Distribution and Out-of-Distribution Label Noise for Robust Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.13389