NeFut Logo NeFut
Admin Login

[CS.AI] Dialogue-Driven Visual Place Recognition: A New Paradigm

Published at: 2026-07-17 22:00 Last updated: 2026-07-18 08:18
#AI #Machine Learning #Open Source

Abstract

Inspired by how humans communicate spatial information, language-guided geo-localization has gained significant traction for its intuitive and practical value. Despite this progress, most methods still rely on a static, one-shot retrieval paradigm, which fails to handle the ambiguity and incompleteness inherent in real-world natural language descriptions. We propose a paradigm shift to reasoning retrieval and introduce Dialogue Place Recognition (DlgPR), which casts localization as an interactive, dialogue-driven reasoning process.

To support this new task, we present DlgQuest-Cities, the first large-scale dialogue-based benchmark for place recognition, and a unified reasoning framework that couples a cross-modal multi-level retriever with an intelligent questioner, DQ-pilot. DQ-pilot is trained in a curriculum: supervised fine-tuning on a curated DQ-cities-20k subset followed by reinforcement refinement on a harder DQ-cities-10k split via GRPO.

Two task-aligned metrics guide learning: a Discriminative Difficulty Index (DDI) for curriculum sampling and a Positional Retrieval Gain (PRG) reward that directly measures retrieval improvement induced by a question. Experiments show this reasoning-based approach significantly outperforms baselines.

The code and model are available at GitHub.

Blogger's Review: This research significantly enhances place recognition accuracy and flexibility by introducing dialogue mechanisms, showcasing new potentials in human-computer interaction, especially in handling complex natural language descriptions effectively.

Original Source: https://arxiv.org/abs/2607.14115

[h] Back to Home