南京师范大学学报（工程技术版）2026，Vol.26Issue(3)：22-30,9.DOI:10.3969/j.issn.1672-1292.2026.03.003
基于分层动态掩码视觉Transformer的长尾图像识别研究
Hierarchical Dynamic Masked Vision Transformer for Long-Tail Image Recognition
摘要
Abstract
Many classification tasks in the real world inherently possess hierarchical semantic structures.When these hierarchical classification tasks simultaneously face long-tailed distributions,the difficulty of recognition is further exacerbated.Existing long-tailed learning methods mostly treat categories as flat structures and fail to fully utilize the inherent semantic correlations in hierarchical labels.Traditional hierarchical classification methods,on the other hand,usually assume balanced category distributions and lack robustness to long-tailed distributions.To address this problem,this paper proposes a long-tailed image recognition algorithm based on a Hierarchical Dynamic Masked Vision Transformer(HDMViT).Aiming at the extremely imbalanced label distribution,the parent-level labels of the dataset are reconstructed to enhance the expressive capability of the hierarchical structure.Proposed methodology reconstructs parent-level labels to strengthen hierarchical representation,specifically targeting extreme label imbalance.Meanwhile,a hierarchical dual-classification-head structure is introduced into the Vision Transformer model,in which both classification heads make decisions based on the same feature vector output by the Transformer encoder:the coarse-grained(parent-level)head directly models the parent-class distribution through fully connected layers,while the fine-grained(child-level)head further incorporates a dynamic logit masking mechanism to filter out irrelevant feature interference,ensuring that the model learns the key features of the target classes in a more focused manner,thereby making more effective use of both fine-grained and coarse-grained semantic information.Experimental results show that the proposed method achieves excellent performance on multiple long-tailed datasets.关键词
深度学习/长尾学习/不平衡数据/视觉Transformer/层次分类Key words
deep learning/long-tail learning/imbalanced data/vision transformer/hierarchical classification分类
信息技术与安全科学引用本文复制引用
汪世豪,毛煜,林耀进..基于分层动态掩码视觉Transformer的长尾图像识别研究[J].南京师范大学学报（工程技术版）,2026,26(3):22-30,9.基金项目
国家自然科学基金资助项目(62576158)、福建省自然科学基金重点项目(2026J002035)、福建省自然科学基金面上项目(2026J001987). （62576158）
