Salvato in:
Dettagli Bibliografici
Autori principali: Choi, Lucas, Greer, Ross
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.09139
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918020144693248
author Choi, Lucas
Greer, Ross
author_facet Choi, Lucas
Greer, Ross
contents Vision-language models (VLMs) offer flexible object detection through natural language prompts but suffer from performance variability depending on prompt phrasing. In this paper, we introduce a method for automated prompt refinement using a novel metric called the Contrastive Class Alignment Score (CCAS), which ranks prompts based on their semantic alignment with a target object class while penalizing similarity to confounding classes. Our method generates diverse prompt candidates via a large language model and filters them through CCAS, computed using prompt embeddings from a sentence transformer. We evaluate our approach on challenging object categories, demonstrating that our automatic selection of high-precision prompts improves object detection accuracy without the need for additional model training or labeled data. This scalable and model-agnostic pipeline offers a principled alternative to manual prompt engineering for VLM-based detection systems.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09139
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond General Prompts: Automated Prompt Refinement using Contrastive Class Alignment Scores for Disambiguating Objects in Vision-Language Models
Choi, Lucas
Greer, Ross
Computer Vision and Pattern Recognition
Vision-language models (VLMs) offer flexible object detection through natural language prompts but suffer from performance variability depending on prompt phrasing. In this paper, we introduce a method for automated prompt refinement using a novel metric called the Contrastive Class Alignment Score (CCAS), which ranks prompts based on their semantic alignment with a target object class while penalizing similarity to confounding classes. Our method generates diverse prompt candidates via a large language model and filters them through CCAS, computed using prompt embeddings from a sentence transformer. We evaluate our approach on challenging object categories, demonstrating that our automatic selection of high-precision prompts improves object detection accuracy without the need for additional model training or labeled data. This scalable and model-agnostic pipeline offers a principled alternative to manual prompt engineering for VLM-based detection systems.
title Beyond General Prompts: Automated Prompt Refinement using Contrastive Class Alignment Scores for Disambiguating Objects in Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.09139