DC-VLAQ: Query-Residual Aggregation for Robust Visual Place Recognition

2026-01-19

AI Summary

This work addresses the challenge of insufficient robustness in global representations for visual place recognition under viewpoint variations, illumination changes, and domain shifts. To this end, we propose a novel approach that leverages the complementary strengths of DINOv2 and CLIP vision foundation models. By introducing a lightweight residual-guided fusion strategy and a VLAQ (Vision-Language Adaptive Query) query-residual global aggregation mechanism, our method effectively integrates learnable query vectors with local token residual responses. This design preserves fine-grained discriminative details while significantly enhancing representation stability. Extensive experiments demonstrate state-of-the-art performance on multiple standard VPR benchmarks—including Pitts30k, Tokyo24/7, and MSLS—with particularly strong robustness under domain shift and long-term appearance variations.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

One of the central challenges in visual place recognition (VPR) is learning a robust global representation that remains discriminative under large viewpoint changes, illumination variations, and severe domain shifts. While visual foundation models (VFMs) provide strong local features, most existing methods rely on a single model, overlooking the complementary cues offered by different VFMs. However, exploiting such complementary information inevitably alters token distributions, which challenges the stability of existing query-based global aggregation schemes. To address these challenges, we propose DC-VLAQ, a representation-centric framework that integrates the fusion of complementary VFMs and robust global aggregation. Specifically, we first introduce a lightweight residual-guided complementary fusion that anchors representations in the DINOv2 feature space while injecting complementary semantics from CLIP through a learned residual correction. In addition, we propose the Vector of Local Aggregated Queries (VLAQ), a query--residual global aggregation scheme that encodes local tokens by their residual responses to learnable queries, resulting in improved stability and the preservation of fine-grained discriminative cues. Extensive experiments on standard VPR benchmarks, including Pitts30k, Tokyo24/7, MSLS, Nordland, SPED, and AmsterTime, demonstrate that DC-VLAQ consistently outperforms strong baselines and achieves state-of-the-art performance, particularly under challenging domain shifts and long-term appearance changes.

Problem

• visual place recognition
• robust representation
• domain shift
• viewpoint change
• illumination variation

Innovation

• visual place recognition
• visual foundation models
• complementary fusion
• residual-guided aggregation
• query-based global representation