Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Chen, Xu, Huiying, Gao, Changxin, Wang, Zeyu, Liu, Yun, Zhu, Xinzhong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911226734313472
author Li, Chen
Xu, Huiying
Gao, Changxin
Wang, Zeyu
Liu, Yun
Zhu, Xinzhong
author_facet Li, Chen
Xu, Huiying
Gao, Changxin
Wang, Zeyu
Liu, Yun
Zhu, Xinzhong
contents Single-source Domain Generalized Object Detection (SDGOD), as a cutting-edge research topic in computer vision, aims to enhance model generalization capability in unseen target domains through single-source domain training. Current mainstream approaches attempt to mitigate domain discrepancies via data augmentation techniques. However, due to domain shift and limited domain-specific knowledge, models tend to fall into the pitfall of spurious correlations. This manifests as the model's over-reliance on simplistic classification features (e.g., color) rather than essential domain-invariant representations like object contours. To address this critical challenge, we propose the Cauvis (Causal Visual Prompts) method. First, we introduce a Cross-Attention Prompts module that mitigates bias from spurious features by integrating visual prompts with cross-attention. To address the inadequate domain knowledge coverage and spurious feature entanglement in visual prompts for single-domain generalization, we propose a dual-branch adapter that disentangles causal-spurious features while achieving domain adaptation via high-frequency feature extraction. Cauvis achieves state-of-the-art performance with 15.9-31.4% gains over existing domain generalization methods on SDGOD datasets, while exhibiting significant robustness advantages in complex interference environments.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19487
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts
Li, Chen
Xu, Huiying
Gao, Changxin
Wang, Zeyu
Liu, Yun
Zhu, Xinzhong
Computer Vision and Pattern Recognition
Single-source Domain Generalized Object Detection (SDGOD), as a cutting-edge research topic in computer vision, aims to enhance model generalization capability in unseen target domains through single-source domain training. Current mainstream approaches attempt to mitigate domain discrepancies via data augmentation techniques. However, due to domain shift and limited domain-specific knowledge, models tend to fall into the pitfall of spurious correlations. This manifests as the model's over-reliance on simplistic classification features (e.g., color) rather than essential domain-invariant representations like object contours. To address this critical challenge, we propose the Cauvis (Causal Visual Prompts) method. First, we introduce a Cross-Attention Prompts module that mitigates bias from spurious features by integrating visual prompts with cross-attention. To address the inadequate domain knowledge coverage and spurious feature entanglement in visual prompts for single-domain generalization, we propose a dual-branch adapter that disentangles causal-spurious features while achieving domain adaptation via high-frequency feature extraction. Cauvis achieves state-of-the-art performance with 15.9-31.4% gains over existing domain generalization methods on SDGOD datasets, while exhibiting significant robustness advantages in complex interference environments.
title Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.19487