UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement

2025-07-01 · Xiao Zhang, Fei Wei, Yong Wang, Wenda Zhao, Feiyi Li, Xiangxiang Chu arxiv

Zero-shot domain adaptation (ZSDA) presents substantial challenges due to the lack of images in the target domain. Previous approaches leverage Vision-Language Models (VLMs) to tackle this challenge, exploiting their zero-shot learning capabilities. However, these methods primarily address domain distribution shifts and overlook the misalignment between the detection task and VLMs, which rely on manually crafted prompts. To overcome these limitations, we propose the unified prompt and representation enhancement (UPRE) framework, which jointly optimizes both textual prompts and visual representations. Specifically, our approach introduces a multi-view domain prompt that combines linguistic domain priors with detection-specific knowledge, and a visual representation enhancement module that produces domain style variations. Furthermore, we introduce multi-level enhancement strategies, including relative domain distance and positive-negative separation, which align multi-modal representations at the image level and capture diverse visual representations at the instance level, respectively. Extensive experiments conducted on nine benchmark datasets demonstrate the superior performance of our framework in ZSDA detection scenarios. Code is available at https://github.com/AMAP-ML/UPRE.

📄 PDF Abstract BibTeX arXiv:2507.00721

Code (0)

등록된 구현이 없습니다.

Tasks

Zero-Shot Learning Domain Adaptation Object Detection

CUPre: Cross-domain Unsupervised Pre-training for Few-Shot Cell Segmentation

2023-10-06 · Weibin Liao, Xuhong LI, Qingzhong Wang, Yanwu Xu 외

While pre-training on object detection tasks, such as Common Objects in Contexts (COCO) [1], could significantly boost the performance of cell segmentation, it still consumes on massive fine-annotated cell images [2] wit…

Cell Segmentation Contrastive Learning Few-shot Instance Segmentation Instance Segmentation+5

PØDA: Prompt-driven Zero-shot Domain Adaptation

2022-12-06 · Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez 외

Domain adaptation has been vastly investigated in computer vision but still requires access to target images at train time, which might be intractable in some uncommon conditions. In this paper, we propose the task of `P…

Domain Adaptation image-classification Image Classification Language Modeling+6

PODA: Prompt-driven Zero-shot Domain Adaptation

2023-01-01 · ICCV 2023 1 · Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez 외

Domain Adaptation image-classification Image Classification Language Modeling+8

SuPreME: A Supervised Pre-training Framework for Multimodal ECG Representation Learning

2025-02-27 · Mingsheng Cai, Jiuming Jiang, Wenhao Huang, Che Liu 외

Cardiovascular diseases are a leading cause of death and disability worldwide. Electrocardiogram (ECG) is critical for diagnosing and monitoring cardiac health, but obtaining large-scale annotated ECG datasets is labor-i…

Diagnostic Representation Learning Self-Supervised Learning zero-shot-classification+1

Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders

2020-08-03 · Qian Wang, Toby P. Breckon

Domain adaptation approaches aim to exploit useful information from the source domain where supervised learning examples are easier to obtain to address a learning problem in the target domain where there is no or limite…

Domain Adaptation Generalized Zero-Shot Learning Zero-Shot Learning