The Overlooked Value of Test-time Reference Sets in Visual Place Recognition

• URL: http://arxiv.org/abs/2510.03751v1
• Date: Sat, 04 Oct 2025 09:29:58 GMT
• Title: The Overlooked Value of Test-time Reference Sets in Visual Place Recognition
• Authors: Mubariz Zaffar, Liangliang Nan, Sebastian Scherer, Julian F. P. Kooij,
• Abstract summary: Given a query image, Visual Place Recognition (VPR) is the task of retrieving an image of the same place from a reference database.<n>Recent works show that some VPR benchmarks are solved by methods using Vision-Foundation-Model backbones.<n>We propose a complementary, unexplored source of information to bridge the train-test domain gap.
• Score: 16.8881222711597
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Given a query image, Visual Place Recognition (VPR) is the task of retrieving an image of the same place from a reference database with robustness to viewpoint and appearance changes. Recent works show that some VPR benchmarks are solved by methods using Vision-Foundation-Model backbones and trained on large-scale and diverse VPR-specific datasets. Several benchmarks remain challenging, particularly when the test environments differ significantly from the usual VPR training datasets. We propose a complementary, unexplored source of information to bridge the train-test domain gap, which can further improve the performance of State-of-the-Art (SOTA) VPR methods on such challenging benchmarks. Concretely, we identify that the test-time reference set, the "map", contains images and poses of the target domain, and must be available before the test-time query is received in several VPR applications. Therefore, we propose to perform simple Reference-Set-Finetuning (RSF) of VPR models on the map, boosting the SOTA (~2.3% increase on average for Recall@1) on these challenging datasets. Finetuned models retain generalization, and RSF works across diverse test datasets.

Related papers

• Cross-Spectral Body Recognition with Side Information Embedding: Benchmarks on LLCM and Analyzing Range-Induced Occlusions on IJB-MDF [51.36007967653781]
  Vision Transformers (ViTs) have demonstrated impressive performance across a wide range of biometric tasks, including face and body recognition.<n>In this work, we adapt a ViT model pretrained on visible (VIS) imagery to the challenging problem of cross-spectral body recognition.<n>Building on this idea, we integrate Side Information Embedding (SIE) and examine the impact of encoding domain and camera information to enhance cross-spectral matching.<n>Surprisingly, our results show that encoding only camera information - without explicitly incorporating domain information - achieves state-of-the-art performance on the LLCM dataset.
  arXiv  Detail & Related papers  (2025-06-10T16:20:52Z)
• To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognition [4.008780119020479]
  We show that modern retrieval systems often reach a point where re-ranking can degrade results, as current VPR datasets are largely saturated.<n>We propose using image matching as a verification step to assess retrieval confidence, demonstrating that inlier counts can reliably predict when re-ranking is beneficial.
  arXiv  Detail & Related papers  (2025-04-08T15:10:10Z)
• QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding [53.69841526266547]
  Fine-tuning a pre-trained Vision-Language Model with new datasets often falls short in optimizing the vision encoder.<n>We introduce QID, a novel, streamlined, architecture-preserving approach that integrates query embeddings into the vision encoder.
  arXiv  Detail & Related papers  (2025-04-03T18:47:16Z)
• Visual-RFT: Visual Reinforcement Fine-Tuning [75.20572976629646]
  Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers.<n>Visual-RFT further extends the application areas of RFT on visual tasks.
  arXiv  Detail & Related papers  (2025-03-03T18:16:32Z)
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
  We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks.<n>Our benchmark features over 10,000 manually verified instructions and spanning diverse visual conditions, object types, and scales.<n>We evaluate several state-of-the-art VLMs to assess performance on geospatial-specific challenges.
  arXiv  Detail & Related papers  (2024-11-28T18:59:56Z)
• EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition [6.996304653818122]
  We present an effective approach to harness the potential of a foundation model for Visual Place Recognition.<n>We show that features extracted from self-attention layers can act as a powerful re-ranker for VPR, even in a zero-shot setting.<n>Our method also demonstrates exceptional robustness and generalization, setting new state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-05-28T11:24:41Z)
• Collaborative Visual Place Recognition through Federated Learning [5.06570397863116]
  Visual Place Recognition (VPR) aims to estimate the location of an image by treating it as a retrieval problem. VPR uses a database of geo-tagged images and leverages deep neural networks to extract a global representation, called descriptor, from each image. This research revisits the task of VPR through the lens of Federated Learning (FL), addressing several key challenges associated with this adaptation.
  arXiv  Detail & Related papers  (2024-04-20T08:48:37Z)
• Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition [72.35438297011176]
  We propose a novel method to realize seamless adaptation of pre-trained models for visual place recognition (VPR) Specifically, to obtain both global and local features that focus on salient landmarks for discriminating places, we design a hybrid adaptation method. Experimental results show that our method outperforms the state-of-the-art methods with less training data and training time.
  arXiv  Detail & Related papers  (2024-02-22T12:55:01Z)
• A-MuSIC: An Adaptive Ensemble System For Visual Place Recognition In Changing Environments [22.58641358408613]
  Visual place recognition (VPR) is an essential component of robot navigation and localization systems. No single VPR technique excels in every environmental condition. adaptive VPR system dubbed Adaptive Multi-Self Identification and Correction (A-MuSIC) A-MuSIC matches or beats state-of-the-art VPR performance across all tested benchmark datasets.
  arXiv  Detail & Related papers  (2023-03-24T19:25:22Z)
• Unified Visual Relationship Detection with Vision and Language Models [89.77838890788638]
  This work focuses on training a single visual relationship detector predicting over the union of label spaces from multiple datasets. We propose UniVRD, a novel bottom-up method for Unified Visual Relationship Detection by leveraging vision and language models. Empirical results on both human-object interaction detection and scene-graph generation demonstrate the competitive performance of our model.
  arXiv  Detail & Related papers  (2023-03-16T00:06:28Z)
• Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition [65.84978547406753]
  Test-time Adaptation aims to adapt the model trained on source domains to yield better predictions for test samples. Single-Utterance Test-time Adaptation (SUTA) is the first TTA study in speech area to our best knowledge.
  arXiv  Detail & Related papers  (2022-03-27T06:38:39Z)
• Analysis on Image Set Visual Question Answering [0.3359875577705538]
  We tackle the challenge of Visual Question Answering in multi-image setting. Traditional VQA tasks have focused on a single-image setting where the target answer is generated from a single image. In this report, we work with 4 approaches in a bid to improve the performance on the task.
  arXiv  Detail & Related papers  (2021-03-31T20:47:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.