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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Sheng, Yan, Jiexuan, Liu, Beiyan, Liu, Bo, Hong, Richang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912599459758080
author Huang, Sheng
Yan, Jiexuan
Liu, Beiyan
Liu, Bo
Hong, Richang
author_facet Huang, Sheng
Yan, Jiexuan
Liu, Beiyan
Liu, Bo
Hong, Richang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17747
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dual-View Alignment Learning with Hierarchical-Prompt for Class-Imbalance Multi-Label Classification
Huang, Sheng
Yan, Jiexuan
Liu, Beiyan
Liu, Bo
Hong, Richang
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Dual-View Alignment Learning with Hierarchical-Prompt for Class-Imbalance Multi-Label Classification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.17747