CVSep 30, 2025

SAGE: Spatial-visual Adaptive Graph Exploration for Visual Place Recognition

arXiv:2509.25723v11 citationsh-index: 19Has Code
Originality Highly original
AI Analysis

This work addresses visual place recognition for robotics and autonomous systems, offering incremental improvements through a novel training pipeline.

The paper tackles the problem of robust visual place recognition under appearance and viewpoint variations by introducing SAGE, a training pipeline that jointly improves local feature aggregation, sample organization, and hard sample mining, achieving state-of-the-art results such as 98.9% Recall@1 on SPED and 100% Recall@10 on SPED with 4096D descriptors.

Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior methods focus on descriptor fine-tuning or fixed sampling strategies yet neglect the dynamic interplay between spatial context and visual similarity during training. We present SAGE (Spatial-visual Adaptive Graph Exploration), a unified training pipeline that enhances granular spatial-visual discrimination by jointly improving local feature aggregation, organize samples during training, and hard sample mining. We introduce a lightweight Soft Probing module that learns residual weights from training data for patch descriptors before bilinear aggregation, boosting distinctive local cues. During training we reconstruct an online geo-visual graph that fuses geographic proximity and current visual similarity so that candidate neighborhoods reflect the evolving embedding landscape. To concentrate learning on the most informative place neighborhoods, we seed clusters from high-affinity anchors and iteratively expand them with a greedy weighted clique expansion sampler. Implemented with a frozen DINOv2 backbone and parameter-efficient fine-tuning, SAGE achieves SOTA across eight benchmarks. It attains 98.9%, 95.8%, 94.5%, and 96.0% Recall@1 on SPED, Pitts30k-test, MSLS-val, and Nordland, respectively. Notably, our method obtains 100% Recall@10 on SPED only using 4096D global descriptors. Code and model will be available at: https://github.com/chenshunpeng/SAGE.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes