RankTuning: Cross-Image Partial Tuning Strategies for Rank Optimization in Visual Place Recognition
- 27 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (12) , 23179-23189
Abstract
Aiming to estimate the location, a common strategy of Visual Place Recognition (VPR) involves utilizing global retrieval to get top-k candidates first and performing local feature matching in candidates for reranking. Although local reranking methods bring performance gains, they need a lot of computational overhead. To narrow the performance gap between global retrieval and local reranking methods with little cost, one method is to rerank candidates with global features. However, previous works only utilized the information from positive samples in candidates, ignoring the fact that negative samples can also provide useful information. To this end, we propose RankTuning, a method that aggregates all the information from candidates using global features for reranking. Specifically, we design a cross-image interaction module that allows all candidates to interact with others to enhance the discriminative power of features. Furthermore, to drive the training of this module, we propose Generalized Recall loss to handle hard samples with a better gradient strategy. Experimental results demonstrate that our method can be easily inserted into existing architectures and achieve state-of-the-art performance. Meanwhile, our method does not require additional storage overhead, and the matching latency is only 6.3% of that of the current fastest local reranking method. The code is released at https://github.com/LKELN/RankTuning.gitKeywords
Funding Information
- National Natural Science Foundation of China (62088102, 62201447)
This publication has 49 references indexed in Scilit:
- GSV-Cities: Toward appropriate supervised visual place recognitionNeurocomputing, 2022
- Unifying Deep Local and Global Features for Image Search2020
- Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval2020
- Self-supervising Fine-Grained Region Similarities for Large-Scale Image Localization2020
- Efficient Optimization for Rank-Based Loss Functions2018
- Deep Residual Learning for Image Recognition2016
- NetVLAD: CNN Architecture for Weakly Supervised Place Recognition2016
- 24/7 place recognition by view synthesis2015
- Visual Place Recognition with Repetitive Structures2013
- SURF: Speeded Up Robust Features2006