Pros: Prompting-to-simulate Generalized Knowledge For Universal Cross-domain Retrieval

Abstract

The goal of Universal Cross-Domain Retrieval (UCDR) is to achieve robust performance in generalized test scenarios, wherein data may belong to strictly unknown domains and categories during training. Recently, pre-trained models with prompt tuning have shown strong generalization capabilities and attained noteworthy achievements in various downstream tasks, such as few-shot learning and video-text retrieval. However, applying them directly to UCDR may not sufficiently to handle both domain shift (i.e., adapting to unfamiliar domains) and semantic shift (i.e., transferring to unknown categories). To this end, we propose \textbf\{Pro\}mpting-to-\textbf\{S\}imulate (ProS), the first method to apply prompt tuning for UCDR. ProS employs a two-step process to simulate Content-aware Dynamic Prompts (CaDP) which can impact models to produce generalized features for UCDR. Concretely, in Prompt Units Learning stage, we introduce two Prompt Units to individually capture domain and semantic knowle

Stats

• citations20
• S2 citations—
• github stars20
• HF likes0
• heat score12.56
• arxiv keyfang2023pros

Related papers

• Ucdr-adapter: Exploring Adaptation Of Pre-trained Vision-language Models For Universal Cross-domain Retrieval (2024)4.52
• Test-time Training For Data-efficient UCDR (2022)0.00
• Parameter-efficient Prompt Tuning Makes Generalized And Calibrated Neural Text Retrievers (2022)5.84
• Fine-grained Retrieval Prompt Tuning (2022)10.07
• Soft Prompt Tuning For Augmenting Dense Retrieval With Large Language Models (2023)9.41
• Semantic Feature Learning For Universal Unsupervised Cross-domain Retrieval (2024)0.00
• Retrieval-augmented Dynamic Prompt Tuning For Incomplete Multimodal Learning (2025)8.87
• DGL: Dynamic Global-local Prompt Tuning For Text-video Retrieval (2024)14.35