English

Dual-View Alignment Learning with Hierarchical-Prompt for Class-Imbalance Multi-Label Classification

Computer Vision and Pattern Recognition 2025-09-23 v1 Artificial Intelligence

Abstract

Real-world datasets often exhibit class imbalance across multiple categories, manifesting as long-tailed distributions and few-shot scenarios. This is especially challenging in Class-Imbalanced Multi-Label Image Classification (CI-MLIC) tasks, where data imbalance and multi-object recognition present significant obstacles. To address these challenges, we propose a novel method termed Dual-View Alignment Learning with Hierarchical Prompt (HP-DVAL), which leverages multi-modal knowledge from vision-language pretrained (VLP) models to mitigate the class-imbalance problem in multi-label settings. Specifically, HP-DVAL employs dual-view alignment learning to transfer the powerful feature representation capabilities from VLP models by extracting complementary features for accurate image-text alignment. To better adapt VLP models for CI-MLIC tasks, we introduce a hierarchical prompt-tuning strategy that utilizes global and local prompts to learn task-specific and context-related prior knowledge. Additionally, we design a semantic consistency loss during prompt tuning to prevent learned prompts from deviating from general knowledge embedded in VLP models. The effectiveness of our approach is validated on two CI-MLIC benchmarks: MS-COCO and VOC2007. Extensive experimental results demonstrate the superiority of our method over SOTA approaches, achieving mAP improvements of 10.0\% and 5.2\% on the long-tailed multi-label image classification task, and 6.8\% and 2.9\% on the multi-label few-shot image classification task.

Keywords

Cite

@article{arxiv.2509.17747,
  title  = {Dual-View Alignment Learning with Hierarchical-Prompt for Class-Imbalance Multi-Label Classification},
  author = {Sheng Huang and Jiexuan Yan and Beiyan Liu and Bo Liu and Richang Hong},
  journal= {arXiv preprint arXiv:2509.17747},
  year   = {2025}
}

Comments

accepted by IEEE Transactions on Image Processing

R2 v1 2026-07-01T05:49:32.905Z