Improving Visual Place Recognition Performance by Maximising Complementarity

• URL: http://arxiv.org/abs/2102.08416v1
• Date: Tue, 16 Feb 2021 19:18:33 GMT
• Title: Improving Visual Place Recognition Performance by Maximising Complementarity
• Authors: Maria Waheed, Michael Milford, Klaus D. McDonald-Maier, Shoaib Ehsan
• Abstract summary: This paper investigates the complementarity of state-of-the-art VPR methods systematically for the first time. It identifies those combinations which can result in better performance. Results are presented for eight state-of-the-art VPR methods on ten widely-used VPR datasets.
• Score: 22.37892767050086
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual place recognition (VPR) is the problem of recognising a previously visited location using visual information. Many attempts to improve the performance of VPR methods have been made in the literature. One approach that has received attention recently is the multi-process fusion where different VPR methods run in parallel and their outputs are combined in an effort to achieve better performance. The multi-process fusion, however, does not have a well-defined criterion for selecting and combining different VPR methods from a wide range of available options. To the best of our knowledge, this paper investigates the complementarity of state-of-the-art VPR methods systematically for the first time and identifies those combinations which can result in better performance. The paper presents a well-defined framework which acts as a sanity check to find the complementarity between two techniques by utilising a McNemar's test-like approach. The framework allows estimation of upper and lower complementarity bounds for the VPR techniques to be combined, along with an estimate of maximum VPR performance that may be achieved. Based on this framework, results are presented for eight state-of-the-art VPR methods on ten widely-used VPR datasets showing the potential of different combinations of techniques for achieving better performance.

Related papers

• Revisiting BPR: A Replicability Study of a Common Recommender System Baseline [78.00363373925758]
  We study the features of the BPR model, indicating their impact on its performance, and investigate open-source BPR implementations. Our analysis reveals inconsistencies between these implementations and the original BPR paper, leading to a significant decrease in performance of up to 50% for specific implementations. We show that the BPR model can achieve performance levels close to state-of-the-art methods on the top-n recommendation tasks and even outperform them on specific datasets.
  arXiv  Detail & Related papers  (2024-09-21T18:39:53Z)
• Improving Out-of-Distribution Detection by Combining Existing Post-hoc Methods [1.747623282473278]
  Post-hoc deep Out-of-Distribution (OOD) detection has expanded rapidly. Current best practice is to test all the methods on the datasets at hand. This paper shifts focus from developing new methods to effectively combining existing ones to enhance OOD detection.
  arXiv  Detail & Related papers  (2024-07-09T15:46:39Z)
• Evaluating Ensemble Methods for News Recommender Systems [50.90330146667386]
  This paper demonstrates how ensemble methods can be used to combine many diverse state-of-the-art algorithms to achieve superior results on the Microsoft News dataset (MIND) Our findings demonstrate that a combination of NRS algorithms can outperform individual algorithms, provided that the base learners are sufficiently diverse.
  arXiv  Detail & Related papers  (2024-06-23T13:40:50Z)
• Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression [63.23578860867408]
  We investigate how to integrate the evaluations of importance and sparsity scores into a single stage. We present OFB, a cost-efficient approach that simultaneously evaluates both importance and sparsity scores. Experiments demonstrate that OFB can achieve superior compression performance over state-of-the-art searching-based and pruning-based methods.
  arXiv  Detail & Related papers  (2024-03-23T13:22:36Z)
• A Complementarity-Based Switch-Fuse System for Improved Visual Place Recognition [19.14779092252812]
  Switch-Fuse is an interesting way to combine the robustness of switching VPR techniques based on complementarity and the force of fusing the carefully selected techniques to significantly improve performance. The system combines two significant processes, switching and fusing VPR techniques, which together as a hybrid model substantially improve performance on all major VPR data sets illustrated using PR curves.
  arXiv  Detail & Related papers  (2023-03-01T18:19:10Z)
• Boosting Performance of a Baseline Visual Place Recognition Technique by Predicting the Maximally Complementary Technique [25.916992891359055]
  One recent promising approach to the Visual Place Recognition problem has been to fuse the place recognition estimates of multiple complementary VPR techniques. These approaches require all potential VPR methods to be brute-force run before they are selectively fused. Here we propose an alternative approach that instead starts with a known single base VPR technique, and learns to predict the most complementary additional VPR technique to fuse with it.
  arXiv  Detail & Related papers  (2022-10-14T04:32:23Z)
• Towards Better Understanding Attribution Methods [77.1487219861185]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We also propose a post-processing smoothing step that significantly improves the performance of some attribution methods.
  arXiv  Detail & Related papers  (2022-05-20T20:50:17Z)
• An Efficient Combinatorial Optimization Model Using Learning-to-Rank Distillation [2.0137632982900207]
  We present the learning-to-rank distillation-based COP framework, where a high-performance ranking policy can be distilled into a non-iterative, simple model. Specifically, we employ the approximated ranking distillation to render a score-based ranking model learnable via gradient descent. We demonstrate that a distilled model achieves comparable performance to its respective, high-performance RL, but also provides several times faster inferences.
  arXiv  Detail & Related papers  (2021-12-24T10:52:47Z)
• Unsupervised Complementary-aware Multi-process Fusion for Visual Place Recognition [28.235055888073855]
  We propose an unsupervised algorithm that finds the most robust set of VPR techniques to use in the current deployment environment. The proposed dynamic multi-process fusion (Dyn-MPF) has superior VPR performance compared to a variety of challenging competitive methods.
  arXiv  Detail & Related papers  (2021-12-09T04:57:33Z)
• Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis [54.94682858474711]
  Class Activation Mapping (CAM) approaches provide an effective visualization by taking weighted averages of the activation maps. We propose a novel set of metrics to quantify explanation maps, which show better effectiveness and simplify comparisons between approaches.
  arXiv  Detail & Related papers  (2021-04-20T21:34:24Z)
• Image Matching across Wide Baselines: From Paper to Practice [80.9424750998559]
  We introduce a comprehensive benchmark for local features and robust estimation algorithms. Our pipeline's modular structure allows easy integration, configuration, and combination of different methods. We show that with proper settings, classical solutions may still outperform the perceived state of the art.
  arXiv  Detail & Related papers  (2020-03-03T15:20:57Z)

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.