Prompt Tuning and Retrieval in Open-Vocabulary Object Detection for Configurable Robot Vision
Year: 2026
Type: conference-paper
Abstract: Robotic vision modules in low-volume high-mixture scenarios frequently need to be adapted to new requirements, but retraining or fine-tuning well-established object detection models may be too slow and resource intensive. Open-vocabulary object detection is a promising alternative, and fine tuning the prompt embeddings can solve situations where text prompts are not sufficient. We propose coupling this so-called prompt tuning with a vector database for retrieving the best prompts to differentiate challenging scenarios. This enables iterative improvement without much impact on the model’s performance with respect to previous requirements. We implemented the proposed method by adapting Grounding DINO and experimentally verified its effectiveness using the LVIS benchmark.
Source: Procedia Computer Science
Authors: Stefan Fixl, Michael Hofmann, Andreas Pichler
Institution: PROFACTOR GmbH (Austria)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7140135577