.png){kind=icon}
.png){kind=icon}
Return
Multiple Contrastive Experts for long-tailed image classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2024.124613.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Real-world image classification data usually exhibits a challenging long-tailed distribution, attributed to the inherent difficulty in data collection. Existing ensemble approaches predominantly prioritize the empirical diversification of the ensemble model, sidelining its critical aspects of representation ability. A noticeable gap also exists in theoretical analysis elucidating the intricate relationship between ensemble model diversity and its generalization efficacy. This paper introduces a loosely coupled ensemble framework, Multiple Contrastive Experts (MCE) tailored for long-tailed image classification, aiming to bolster image representation while ensuring diversity within the proposed MCE. Leveraging skill-diverse classification losses, the experts in the ensemble model are able to specialize in different kinds of classes in the long-tailed distribution. An adapted supervised contrastive learning (SCL) loss is introduced to guide training for each feature learning branch to enhance the representation ability of MCE. Through the effective integration of the different losses from all experts, each expert model can be optimized coordinately. Moreover, the relationship between the generalization ability of MCE and its diversity is theoretically revealed against a single classification model. At last, extensive experiments were made over five widely used long-tailed image classification datasets. The results show that our proposed MCE is very competitive against the state-of-the-art methods, while maintaining a relatively lower computational cost. Besides, MCE has also exhibited superior performance with an increasing number of experts.
Keywords:
Long-tailed image classification
Loosely coupled ensemble model
Multiple contrastive experts
Supervised contrastive learning
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W