RICASSO: Reinforced Imbalance Learning with Class-Aware Self-Supervised Outliers Exposure
In real-world scenarios, deep learning models often face challenges from both imbalanced (long-tailed) and out-of-distribution (OOD) data. However, existing joint methods rely on real OOD data, which leads to unnecessary trade-offs. In contrast, our research shows that data mixing, a potent augmenta...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | In real-world scenarios, deep learning models often face challenges from both
imbalanced (long-tailed) and out-of-distribution (OOD) data. However, existing
joint methods rely on real OOD data, which leads to unnecessary trade-offs. In
contrast, our research shows that data mixing, a potent augmentation technique
for long-tailed recognition, can generate pseudo-OOD data that exhibit the
features of both in-distribution (ID) data and OOD data. Therefore, by using
mixed data instead of real OOD data, we can address long-tailed recognition and
OOD detection holistically. We propose a unified framework called Reinforced
Imbalance Learning with Class-Aware Self-Supervised Outliers Exposure
(RICASSO), where "self-supervised" denotes that we only use ID data for outlier
exposure. RICASSO includes three main strategies: Norm-Odd-Duality-Based
Outlier Exposure: Uses mixed data as pseudo-OOD data, enabling simultaneous ID
data rebalancing and outlier exposure through a single loss function.
Ambiguity-Aware Logits Adjustment: Utilizes the ambiguity of ID data to
adaptively recalibrate logits. Contrastive Boundary-Center Learning: Combines
Virtual Boundary Learning and Dual-Entropy Center Learning to use mixed data
for better feature separation and clustering, with Representation Consistency
Learning for robustness. Extensive experiments demonstrate that RICASSO
achieves state-of-the-art performance in long-tailed recognition and
significantly improves OOD detection compared to our baseline (27% improvement
in AUROC and 61% reduction in FPR on the iNaturalist2018 dataset). On
iNaturalist2018, we even outperforms methods using real OOD data. The code will
be made public soon. |
---|---|
DOI: | 10.48550/arxiv.2410.10548 |