Boosting Performance of a Baseline Visual Place Recognition Technique by Predicting the Maximally Complementary Technique

• URL: http://arxiv.org/abs/2210.07509v1
• Date: Fri, 14 Oct 2022 04:32:23 GMT
• Title: Boosting Performance of a Baseline Visual Place Recognition Technique by Predicting the Maximally Complementary Technique
• Authors: Connor Malone and Stephen Hausler and Tobias Fischer and Michael Milford
• Abstract summary: 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.
• Score: 25.916992891359055
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: One recent promising approach to the Visual Place Recognition (VPR) problem has been to fuse the place recognition estimates of multiple complementary VPR techniques using methods such as SRAL and multi-process fusion. These approaches come with a substantial practical limitation: they require all potential VPR methods to be brute-force run before they are selectively fused. The obvious solution to this limitation is to predict the viable subset of methods ahead of time, but this is challenging because it requires a predictive signal within the imagery itself that is indicative of high performance methods. 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, that results in the largest improvement in performance. The key innovation here is to use a dimensionally reduced difference vector between the query image and the top-retrieved reference image using this baseline technique as the predictive signal of the most complementary additional technique, both during training and inference. We demonstrate that our approach can train a single network to select performant, complementary technique pairs across datasets which span multiple modes of transportation (train, car, walking) as well as to generalise to unseen datasets, outperforming multiple baseline strategies for manually selecting the best technique pairs based on the same training data.

Related papers

• UAV-enabled Collaborative Beamforming via Multi-Agent Deep Reinforcement Learning [79.16150966434299]
  We formulate a UAV-enabled collaborative beamforming multi-objective optimization problem (UCBMOP) to maximize the transmission rate of the UVAA and minimize the energy consumption of all UAVs. We use the heterogeneous-agent trust region policy optimization (HATRPO) as the basic framework, and then propose an improved HATRPO algorithm, namely HATRPO-UCB.
  arXiv  Detail & Related papers  (2024-04-11T03:19:22Z)
• Generalized Correspondence Matching via Flexible Hierarchical Refinement and Patch Descriptor Distillation [13.802788788420175]
  Correspondence matching plays a crucial role in numerous robotics applications. This paper addresses the limitations of deep feature matching (DFM), a state-of-the-art (SoTA) plug-and-play correspondence matching approach. Our proposed method achieves an overall performance in terms of mean matching accuracy of 0.68, 0.92, and 0.95 with respect to the tolerances of 1, 3, and 5 pixels, respectively.
  arXiv  Detail & Related papers  (2024-03-08T15:32:18Z)
• DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection [72.25697820290502]
  This work introduces a straightforward and efficient strategy to identify potential novel classes through zero-shot classification. We refer to this approach as the self-training strategy, which enhances recall and accuracy for novel classes without requiring extra annotations, datasets, and re-training. Empirical evaluations on three datasets, including LVIS, V3Det, and COCO, demonstrate significant improvements over the baseline performance.
  arXiv  Detail & Related papers  (2023-10-02T17:52:24Z)
• 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)
• Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information [77.80071279597665]
  We propose an all-in-one single-stage pre-training approach, named Maximizing Multi-modal Mutual Information Pre-training (M3I Pre-training) Our approach achieves better performance than previous pre-training methods on various vision benchmarks, including ImageNet classification, object detection, LVIS long-tailed object detection, and ADE20k semantic segmentation.
  arXiv  Detail & Related papers  (2022-11-17T18:59:49Z)
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
  We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
  arXiv  Detail & Related papers  (2022-10-11T08:24:50Z)
• Distributed Adversarial Training to Robustify Deep Neural Networks at Scale [100.19539096465101]
  Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification. To defend against such attacks, an effective approach, known as adversarial training (AT), has been shown to mitigate robust training. We propose a large-batch adversarial training framework implemented over multiple machines.
  arXiv  Detail & Related papers  (2022-06-13T15:39:43Z)
• Towards a Unified Approach to Homography Estimation Using Image Features and Pixel Intensities [0.0]
  The homography matrix is a key component in various vision-based robotic tasks. Traditionally, homography estimation algorithms are classified into feature- or intensity-based. This paper proposes a new hybrid method that unifies both classes into a single nonlinear optimization procedure.
  arXiv  Detail & Related papers  (2022-02-20T02:47:05Z)
• 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)
• Improving Visual Place Recognition Performance by Maximising Complementarity [22.37892767050086]
  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.
  arXiv  Detail & Related papers  (2021-02-16T19:18:33Z)
• Deep Unfolding Network for Image Super-Resolution [159.50726840791697]
  This paper proposes an end-to-end trainable unfolding network which leverages both learning-based methods and model-based methods. The proposed network inherits the flexibility of model-based methods to super-resolve blurry, noisy images for different scale factors via a single model.
  arXiv  Detail & Related papers  (2020-03-23T17:55:42Z)

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.