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

TL;DR

AEON is a novel one-stage method that dynamically estimates in-distribution and out-of-distribution label noise rates, improving robustness in noisy image classification and introducing a new benchmark for real-world scenarios.

Contribution

It introduces AEON, an efficient one-stage approach for estimating instance-dependent ID and OOD label noise, addressing gaps in existing methods and benchmarks.

Findings

AEON achieves state-of-the-art results on synthetic datasets.

AEON performs well on real-world noisy datasets.

The new benchmark reflects complex real-world noise scenarios.

Abstract

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