HGLTR: Hierarchical Knowledge Injection for Calibrating Pre-trained Models in Long-Tail Recognition
Jinpeng Zheng, Shao-Yuan Li, Gan Xu, Wenhai Wan, Zijian Tao, Songcan Chen, Kangkan Wang
Abstract
Long-tail recognition remains challenging for pre-trained foundation models like CLIP, which often suffer from performance degradation under imbalanced data. This stems not only from the overfitting/underfitting issues during fine-tuning but, more fundamentally, from the inherent bias inherited from the long-tail distribution of their massive pre-training datasets. To address this, we propose HGLTR (Hierarchy-Guided Long-Tail Recognition), a novel framework that calibrates pre-trained models by injecting objective class hierarchy knowledge. We argue that the semantic proximity defined by a hierarchy provides a robust, data-independent prior to counteract model bias. Our method is specifically designed for vision-language models
BibTeX
@inproceedings{aaai2026_hgltrhierarchica,
title = {HGLTR: Hierarchical Knowledge Injection for Calibrating Pre-trained Models in Long-Tail Recognition},
author = {Jinpeng Zheng and Shao-Yuan Li and Gan Xu and Wenhai Wan and Zijian Tao and Songcan Chen and Kangkan Wang},
booktitle = {AAAI 2026},
year = {2026}
}