Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jiang, Yuqiu, Qiao, Xiaozhen, Chen, Yifan, Zheng, Ye, Sun, Zhe, Li, Xuelong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917329272569856
author Jiang, Yuqiu
Qiao, Xiaozhen
Chen, Yifan
Zheng, Ye
Sun, Zhe
Li, Xuelong
author_facet Jiang, Yuqiu
Qiao, Xiaozhen
Chen, Yifan
Zheng, Ye
Sun, Zhe
Li, Xuelong
contents Human-Object Interaction (HOI) detection is a fundamental task in computer vision, empowering machines to comprehend human-object relationships in diverse real-world scenarios. Recent advances in VLMs have significantly improved HOI detection by leveraging rich cross-modal representations. However, most existing VLM-based approaches rely heavily on additional training or prompt tuning, resulting in substantial computational overhead and limited scalability, particularly in long-tailed scenarios where rare interactions are severely underrepresented. In this paper, we propose the Adaptive Diversity Cache (ADC) module, a novel training-free and plug-and-play mechanism designed to mitigate long-tail bias in HOI detection. ADC constructs class-specific caches that accumulate high-confidence and diverse feature representations during inference. The method incorporates adaptive capacity allocation favoring rare categories and dynamic feature augmentation to enable robust prediction calibration without requiring additional training or fine-tuning. Extensive experiments on HICO-DET and V-COCO datasets show that ADC consistently improves existing HOI detectors, particularly enhancing rare category detection while preserving overall performance. These findings confirm the effectiveness of ADC as a training-free, plug-and-play solution for long-tail bias mitigation.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18811
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache
Jiang, Yuqiu
Qiao, Xiaozhen
Chen, Yifan
Zheng, Ye
Sun, Zhe
Li, Xuelong
Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Object Interaction (HOI) detection is a fundamental task in computer vision, empowering machines to comprehend human-object relationships in diverse real-world scenarios. Recent advances in VLMs have significantly improved HOI detection by leveraging rich cross-modal representations. However, most existing VLM-based approaches rely heavily on additional training or prompt tuning, resulting in substantial computational overhead and limited scalability, particularly in long-tailed scenarios where rare interactions are severely underrepresented. In this paper, we propose the Adaptive Diversity Cache (ADC) module, a novel training-free and plug-and-play mechanism designed to mitigate long-tail bias in HOI detection. ADC constructs class-specific caches that accumulate high-confidence and diverse feature representations during inference. The method incorporates adaptive capacity allocation favoring rare categories and dynamic feature augmentation to enable robust prediction calibration without requiring additional training or fine-tuning. Extensive experiments on HICO-DET and V-COCO datasets show that ADC consistently improves existing HOI detectors, particularly enhancing rare category detection while preserving overall performance. These findings confirm the effectiveness of ADC as a training-free, plug-and-play solution for long-tail bias mitigation.
title Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.18811