Uncertainty-guided label correction with wavelet-transformed discriminative representation enhancement.
Neural Netw
; 176: 106383, 2024 Aug.
Article
de En
| MEDLINE
| ID: mdl-38781758
ABSTRACT
Label noises, categorized into closed-set noise and open-set noise, are prevalent in real-world scenarios and can seriously hinder the generalization ability of models. Identifying noise is challenging because noisy samples closely resemble true positives. Existing approaches often assume a single noise source, oversimplify closed-set noise, or treat open-set noise as toxic and eliminate it, resulting in limited practical effects. To address these issues, we present a novel approach named uncertainty-guided label correction with wavelet-transformed discriminative representation enhancement (Ultra), designed to mitigate the effects of mixed noise. Specifically, our approach considers a more practical noise setting. To achieve robust mixed-noise identification, we initially look into a learnable wavelet filter for obtaining discriminative features and filtering spurious cues automatically at the representation level. Subsequently, we introduce a two-fold uncertainty estimation to stably locate noise within the corrupted supervised signal level. These insights pave the way for a simple yet potent label correction technique, enabling comprehensive utilization of open-set noise, which can be rendered non-toxic in a specific manner, in contrast to harmful closed-set noise. Experimental validation on datasets with synthetic mixed noise, web noise corruption, and a real-world dataset confirms the effectiveness and generality of Ultra. Furthermore, our approach enhances the application of efficient techniques (e.g., supervised contrastive learning) within label noise scenarios.
Mots clés
Texte intégral:
1
Collection:
01-internacional
Base de données:
MEDLINE
Sujet principal:
Analyse en ondelettes
Limites:
Humans
Langue:
En
Journal:
Neural Netw
Sujet du journal:
NEUROLOGIA
Année:
2024
Type de document:
Article