Multi-Modal Guided Multi-Source Domain Adaptation for Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Sangin, Kwon, Seokjun, Shin, Jeongmin, Kim, Namil, Choi, Yukyung
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916008691761152
author Lee, Sangin
Kwon, Seokjun
Shin, Jeongmin
Kim, Namil
Choi, Yukyung
author_facet Lee, Sangin
Kwon, Seokjun
Shin, Jeongmin
Kim, Namil
Choi, Yukyung
contents General object detection (OD) struggles to detect objects in the target domain that differ from the training distribution. To address this, recent studies demonstrate that training from multiple source domains and explicitly processing them separately for multi-source domain adaptation (MSDA) outperforms blending them for unsupervised domain adaptation (UDA). However, existing MSDA methods learn domain-agnostic features from domain-specific RGB images while preserving domain-specific information from the domain-agnostic feature map. To address this, we propose MS-DePro: Multi-Source Detector with Depth and Prompt, composed of (1) depth-guided localization and (2) multi-modal guided prompt learning. We leverage domain-agnostic input modalities, namely depth maps and text, to encode domain-agnostic characteristics. Specifically, we utilize depth maps to generate domain-agnostic region proposals for localization and integrate multi-modal features to align learnable text embeddings for classification. MS-DePro achieves state-of-the-art performance on MSDA benchmarks, and comprehensive ablations demonstrate the effectiveness of our contributions. Our code is available on https://github.com/sejong-rcv/Multi-Modal-Guided-Multi-Source-Domain-Adaptation-for-Object-Detection.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13140
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-Modal Guided Multi-Source Domain Adaptation for Object Detection
Lee, Sangin
Kwon, Seokjun
Shin, Jeongmin
Kim, Namil
Choi, Yukyung
Computer Vision and Pattern Recognition
General object detection (OD) struggles to detect objects in the target domain that differ from the training distribution. To address this, recent studies demonstrate that training from multiple source domains and explicitly processing them separately for multi-source domain adaptation (MSDA) outperforms blending them for unsupervised domain adaptation (UDA). However, existing MSDA methods learn domain-agnostic features from domain-specific RGB images while preserving domain-specific information from the domain-agnostic feature map. To address this, we propose MS-DePro: Multi-Source Detector with Depth and Prompt, composed of (1) depth-guided localization and (2) multi-modal guided prompt learning. We leverage domain-agnostic input modalities, namely depth maps and text, to encode domain-agnostic characteristics. Specifically, we utilize depth maps to generate domain-agnostic region proposals for localization and integrate multi-modal features to align learnable text embeddings for classification. MS-DePro achieves state-of-the-art performance on MSDA benchmarks, and comprehensive ablations demonstrate the effectiveness of our contributions. Our code is available on https://github.com/sejong-rcv/Multi-Modal-Guided-Multi-Source-Domain-Adaptation-for-Object-Detection.
title Multi-Modal Guided Multi-Source Domain Adaptation for Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.13140