A Deeper Look into Second-Order Feature Aggregation for LiDAR Place Recognition

• URL: http://arxiv.org/abs/2409.15919v2
• Date: Mon, 19 May 2025 01:46:57 GMT
• Title: A Deeper Look into Second-Order Feature Aggregation for LiDAR Place Recognition
• Authors: Saimunur Rahman, Peyman Moghadam,
• Abstract summary: LiDAR Place Recognition (LPR) compresses dense pointwise features into compact global descriptors.<n>First-order aggregators such as GeM and NetVLAD are widely used, but they overlook inter-feature correlations that second-order aggregation naturally captures.<n>Channel Partition-based Second-order Local Feature Aggregation (CPS) is a drop-in, partition-based second-order aggregation module that preserves all channels while producing an order-of-magnitude smaller descriptor.
• Score: 4.358456799125694
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Efficient LiDAR Place Recognition (LPR) compresses dense pointwise features into compact global descriptors. While first-order aggregators such as GeM and NetVLAD are widely used, they overlook inter-feature correlations that second-order aggregation naturally captures. Full covariance, a common second-order aggregator, is high in dimensionality; as a result, practitioners often insert a learned projection or employ random sketches -- both of which either sacrifice information or increase parameter count. However, no prior work has systematically investigated how first- and second-order aggregation perform under constrained feature and compute budgets. In this paper, we first demonstrate that second-order aggregation retains its superiority for LPR even when channels are pruned and backbone parameters are reduced. Building on this insight, we propose Channel Partition-based Second-order Local Feature Aggregation (CPS): a drop-in, partition-based second-order aggregation module that preserves all channels while producing an order-of-magnitude smaller descriptor. CPS matches or exceeds the performance of full covariance and outperforms random projection variants, delivering new state-of-the-art results with only four additional learnable parameters across four large-scale benchmarks: Oxford RobotCar, In-house, MulRan, and WildPlaces.

Related papers

• AHDMIL: Asymmetric Hierarchical Distillation Multi-Instance Learning for Fast and Accurate Whole-Slide Image Classification [51.525891360380285]
  AHDMIL is an Asymmetric Hierarchical Distillation Multi-Instance Learning framework.<n>It eliminates irrelevant patches through a two-step training process.<n>It consistently outperforms previous state-of-the-art methods in both classification performance and inference speed.
  arXiv  Detail & Related papers  (2025-08-07T07:47:16Z)
• Nonparametric Bellman Mappings for Value Iteration in Distributed Reinforcement Learning [3.5051814539447474]
  This paper introduces novel Bellman mappings (B-Maps) for value iteration (VI) in distributed reinforcement learning (DRL) B-Maps operate on Q-functions represented in a kernel Hilbert space, enabling a nonparametric formulation. Numerical experiments on two well-known control problems demonstrate the superior performance of the proposed nonparametric B-Maps.
  arXiv  Detail & Related papers  (2025-03-20T14:39:21Z)
• Source-free Semantic Regularization Learning for Semi-supervised Domain Adaptation [25.51051224329922]
  Semi-supervised domain adaptation (SSDA) has been extensively researched due to its ability to improve classification performance and generalization ability of models. We propose a novel SSDA learning framework called semantic regularization learning (SERL) SERL captures the target semantic information from multiple perspectives of regularization learning to achieve adaptive fine-tuning of the source pre-trained model on the target domain.
  arXiv  Detail & Related papers  (2025-01-02T07:53:02Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Accelerating spherical K-means clustering for large-scale sparse document data [0.7366405857677226]
  This paper presents an accelerated spherical K-means clustering algorithm for large-scale and high-dimensional sparse document data sets. We experimentally demonstrate that our algorithm efficiently achieves superior speed performance in large-scale documents compared with algorithms using the state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-11-18T05:50:58Z)
• A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling [54.05517338122698]
  A popular similarity-based feature upsampling pipeline has been proposed, which utilizes a high-resolution feature as guidance.<n>We propose an explicitly controllable query-key feature alignment from both semantic-aware and detail-aware perspectives.<n>We develop a fine-grained neighbor selection strategy on HR features, which is simple yet effective for alleviating mosaic artifacts.
  arXiv  Detail & Related papers  (2024-07-02T14:12:21Z)
• Regularized Projection Matrix Approximation with Applications to Community Detection [1.3761665705201904]
  This paper introduces a regularized projection matrix approximation framework designed to recover cluster information from the affinity matrix. We investigate three distinct penalty functions, each specifically tailored to address bounded, positive, and sparse scenarios. Numerical experiments conducted on both synthetic and real-world datasets reveal that our regularized projection matrix approximation approach significantly outperforms state-of-the-art methods in clustering performance.
  arXiv  Detail & Related papers  (2024-05-26T15:18:22Z)
• Synergistic eigenanalysis of covariance and Hessian matrices for enhanced binary classification [72.77513633290056]
  We present a novel approach that combines the eigenanalysis of a covariance matrix evaluated on a training set with a Hessian matrix evaluated on a deep learning model. Our method captures intricate patterns and relationships, enhancing classification performance.
  arXiv  Detail & Related papers  (2024-02-14T16:10:42Z)
• Weakly supervised covariance matrices alignment through Stiefel matrices estimation for MEG applications [64.20396555814513]
  This paper introduces a novel domain adaptation technique for time series data, called Mixing model Stiefel Adaptation (MSA) We exploit abundant unlabeled data in the target domain to ensure effective prediction by establishing pairwise correspondence with equivalent signal variances between domains. MSA outperforms recent methods in brain-age regression with task variations using magnetoencephalography (MEG) signals from the Cam-CAN dataset.
  arXiv  Detail & Related papers  (2024-01-24T19:04:49Z)
• Optimal Transport Aggregation for Visual Place Recognition [9.192660643226372]
  We introduce SALAD, which reformulates NetVLAD's soft-assignment of local features to clusters as an optimal transport problem. In SALAD, we consider both feature-to-cluster and cluster-to-feature relations and we also introduce a 'dustbin' cluster, designed to selectively discard features deemed non-informative. Our single-stage method surpasses single-stage baselines in public VPR datasets, but also surpasses two-stage methods that add a re-ranking with significantly higher cost.
  arXiv  Detail & Related papers  (2023-11-27T15:46:19Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• Federated Representation Learning via Maximal Coding Rate Reduction [109.26332878050374]
  We propose a methodology to learn low-dimensional representations from a dataset that is distributed among several clients. Our proposed method, which we refer to as FLOW, utilizes MCR2 as the objective of choice, hence resulting in representations that are both between-class discriminative and within-class compressible.
  arXiv  Detail & Related papers  (2022-10-01T15:43:51Z)
• Contrastive Conditional Neural Processes [45.70735205041254]
  Conditional Neural Processes(CNPs) bridge neural networks with probabilistic inference to approximate functions of Processes under meta-learning settings. Two auxiliary contrastive branches are set up hierarchically, namely in-instantiation temporal contrastive learning(tt TCL) and cross-instantiation function contrastive learning(tt FCL) We empirically show that tt TCL captures high-level abstraction of observations, whereas tt FCL helps identify underlying functions, which in turn provides more efficient representations.
  arXiv  Detail & Related papers  (2022-03-08T10:08:45Z)
• Random Ferns for Semantic Segmentation of PolSAR Images [0.0]
  This paper extends the Random Fern framework to the semantic segmentation of polarimetric synthetic aperture radar images. Two distinct optimization strategies are proposed. Experiments show that results can be achieved that are similar to a more complex Random Forest model.
  arXiv  Detail & Related papers  (2022-02-07T20:22:57Z)
• Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization [77.8735802150511]
  We propose a cross-sample adversarial debiasing (CSAD) method to remove the bias information misused by the target task. The correlation measurement plays a critical role in adversarial debiasing and is conducted by a cross-sample neural mutual information estimator. We conduct thorough experiments on publicly available datasets to validate the advantages of the proposed method over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-08-11T21:17:02Z)
• A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation [68.10621089649486]
  We propose Attention Aggregation based Feature Pyramid Network (A2-FPN) to improve multi-scale feature learning. A2-FPN achieves an improvement of 2.0% and 1.4% mask AP when integrated into the strong baselines such as Cascade Mask R-CNN and Hybrid Task Cascade.
  arXiv  Detail & Related papers  (2021-05-07T11:51:08Z)
• Self-supervised asymmetric deep hashing with margin-scalable constraint for image retrieval [3.611160663701664]
  We propose a novel self-supervised asymmetric deep hashing method with a margin-scalable constraint(SADH) approach for image retrieval. SADH implements a self-supervised network to preserve semantic information in a semantic feature map and a semantic code map for the semantics of the given dataset. For the feature learning part, a new margin-scalable constraint is employed for both highly-accurate construction of pairwise correlations in the hamming space and a more discriminative hash code representation.
  arXiv  Detail & Related papers  (2020-12-07T16:09:37Z)
• Robust Locality-Aware Regression for Labeled Data Classification [5.432221650286726]
  We propose a new discriminant feature extraction framework, namely Robust Locality-Aware Regression (RLAR) In our model, we introduce a retargeted regression to perform the marginal representation learning adaptively instead of using the general average inter-class margin. To alleviate the disturbance of outliers and prevent overfitting, we measure the regression term and locality-aware term together with the regularization term by the L2,1 norm.
  arXiv  Detail & Related papers  (2020-06-15T11:36:59Z)
• A Generic Network Compression Framework for Sequential Recommender Systems [71.81962915192022]
  Sequential recommender systems (SRS) have become the key technology in capturing user's dynamic interests and generating high-quality recommendations. We propose a compressed sequential recommendation framework, termed as CpRec, where two generic model shrinking techniques are employed. By the extensive ablation studies, we demonstrate that the proposed CpRec can achieve up to 4$sim$8 times compression rates in real-world SRS datasets.
  arXiv  Detail & Related papers  (2020-04-21T08:40:55Z)
• A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms [67.67377846416106]
  We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We show that value-based methods such as TD($lambda$) and $Q$-Learning have update rules which are contractive in the space of distributions of functions.
  arXiv  Detail & Related papers  (2020-03-27T05:13:29Z)
• Learning Flat Latent Manifolds with VAEs [16.725880610265378]
  We propose an extension to the framework of variational auto-encoders, where the Euclidean metric is a proxy for the similarity between data points. We replace the compact prior typically used in variational auto-encoders with a recently presented, more expressive hierarchical one. We evaluate our method on a range of data-sets, including a video-tracking benchmark.
  arXiv  Detail & Related papers  (2020-02-12T09:54:52Z)
• Supervised Learning for Non-Sequential Data: A Canonical Polyadic Decomposition Approach [85.12934750565971]
  Efficient modelling of feature interactions underpins supervised learning for non-sequential tasks. To alleviate this issue, it has been proposed to implicitly represent the model parameters as a tensor. For enhanced expressiveness, we generalize the framework to allow feature mapping to arbitrarily high-dimensional feature vectors.
  arXiv  Detail & Related papers  (2020-01-27T22:38:40Z)
• Asymmetric Correlation Quantization Hashing for Cross-modal Retrieval [11.988383965639954]
  Cross-modal hashing methods have attracted extensive attention in similarity retrieval across the heterogeneous modalities. ACQH is a novel Asymmetric Correlation Quantization Hashing (ACQH) method proposed in this paper. It learns the projection matrixs of heterogeneous modalities data points for transforming query into a low-dimensional real-valued vector in latent semantic space. It constructs the stacked compositional quantization embedding in a coarse-to-fine manner for indicating database points by a series of learnt real-valued codeword.
  arXiv  Detail & Related papers  (2020-01-14T04:53:30Z)

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.