Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning

• URL: http://arxiv.org/abs/2605.20551v1
• Date: Tue, 19 May 2026 23:01:57 GMT
• Title: Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning
• Abstract summary: Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database.<n>We introduce WeiToP, a VPR-oriented token pruning framework that reduces feature extraction cost via self-distillation.<n>WeiToP enables plug-and-play token pruning at inference time, allowing flexible and on-demand control over the accuracy-efficiency trade-off without additional training.
• Score: 27.4981354426677
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database. Recent state-of-the-art methods employ Vision Transformers (ViTs) as backbone foundation models to extract patch-level features that are robust to viewpoint, illumination, and seasonal variations, which are then aggregated into a compact global descriptor for retrieval. Most existing aggregation methods uniformly pool patch tokens into learned clusters, despite the fact that different clusters often encode distinct spatial or semantic patterns and contribute unequally to VPR performance. To address this limitation, we propose Weighted Aggregated Descriptor (WeiAD), which assigns weights to clusters during aggregation, producing more discriminative global representations. Beyond accuracy, retrieval latency is a critical concern for large-scale deployments and resource-constrained edge devices. Prior work mainly reduces latency by compressing global descriptors, while overlooking the cost of feature extraction, an issue exacerbated by ViT-based backbones. We therefore introduce WeiToP, a VPR-oriented token pruning framework that reduces feature extraction cost via self-distillation, where aggregation-induced token importance supervises a lightweight pruning module attached to an early transformer layer, enabling inference-time token pruning. After a single joint training phase, WeiToP enables plug-and-play token pruning at inference time, allowing flexible and on-demand control over the accuracy-efficiency trade-off without additional training. Moreover, WeiToP outperforms existing token pruning methods adapted from general vision tasks.

Related papers

• Decoupled I/O-Dominant Pipelines for Large-Scale Whole-Slide Image Embedding Extraction [12.996943804893661]
  Whole-slide images (WSIs) are central to computational pathology but are prohibitively large, making patch-based processing the practical unit for foundation model inference.<n>We present a decoupled, I/O-aware pipeline for large-scale WSI embedding extraction that decomposes the workflow into three stages.<n>This design isolates data movement from compute, enabling efficient patch delivery, scalable multi-node inference with minimal communication.
  arXiv  Detail & Related papers  (2026-08-27T15:53:16Z)
• PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding [88.17174909130188]
  Large Vision-Language Models (LVLMs) map visual inputs into dense token sequences, imposing a quadratic computational bottleneck for inference.<n>We introduce PARCEL, a visual tokenization architecture that dynamically partitions the labor of feature extraction.<n>We show that PARCEL consistently outperforms existing matryoshka baselines across visual-token budgets while preserving the "train once, deploy anywhere" paradigm.
  arXiv  Detail & Related papers  (2026-05-28T15:57:31Z)
• RCP: Representation Consistency Pruner for Mitigating Distribution Shift in Large Vision-Language Models [24.3914653184824]
  Large Vision-Language Models (LVLMs) suffer from prohibitive inference costs due to the massive number of visual tokens processed by the language decoder.<n>Existing pruning methods often lead to significant performance degradation because the irreversible removal of visual tokens causes a distribution shift in the hidden states that deviates from the pre-trained full-token regime.<n>We propose Consistency Representation Pruner, which integrates cumulative visual token pruning with a delayed repair mechanism.
  arXiv  Detail & Related papers  (2026-04-04T13:31:45Z)
• FedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Prompts [48.952949805624904]
  Vision Transformer (ViT) is widely adopted, but its global attention often fails to distinguish pedestrians from high similarity backgrounds or diverse viewpoints.<n>To address this, we propose Federated Body Distribution Aware VisualPrompt (FedBPrompt)<n>FedBPrompt introduces learnable visual prompts to guide Transformer attention toward pedestrian-centric regions.
  arXiv  Detail & Related papers  (2026-03-13T11:29:36Z)
• Saccadic Vision for Fine-Grained Visual Classification [10.681604440788854]
  Fine-grained visual classification (FGVC) requires distinguishing between visually similar categories through subtle, localized features.<n>Existing part-based methods rely on complex localization networks that learn mappings from pixel to sample space.<n>We propose a two-stage process that first extracts peripheral features and generates a sample map.<n>We employ contextualized selective attention to weigh the impact of each fixation patch before fusing peripheral and focus representations.
  arXiv  Detail & Related papers  (2025-09-19T07:03:37Z)
• Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference [54.53508601749513]
  We propose a task-oriented feature compression (TOFC) method for multimodal understanding in a device-edge co-inference framework.<n>To enhance compression efficiency, multiple entropy models are adaptively selected based on the characteristics of the visual features.<n>Results show that TOFC achieves up to 52% reduction in data transmission overhead and 63% reduction in system latency.
  arXiv  Detail & Related papers  (2025-03-17T08:37:22Z)
• FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term 3D Object Detection [9.291995455336929]
  We propose a Focal Token Acquring-and-Scaling Transformer (FASTer)<n>FASTer condenses token sequences in an adaptive and lightweight manner.<n>It significantly outperforms other state-of-the-art detectors in both performance and efficiency.
  arXiv  Detail & Related papers  (2025-02-28T03:15:33Z)
• HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models [96.76995840807615]
  HiRes-LLaVA is a novel framework designed to process any size of high-resolution input without altering the original contextual and geometric information. HiRes-LLaVA comprises two innovative components: (i) a SliceRestore adapter that reconstructs sliced patches into their original form, efficiently extracting both global and local features via down-up-sampling and convolution layers, and (ii) a Self-Mining Sampler to compress the vision tokens based on themselves.
  arXiv  Detail & Related papers  (2024-07-11T17:42:17Z)
• Semi-Supervised Coupled Thin-Plate Spline Model for Rotation Correction and Beyond [84.56978780892783]
  We propose CoupledTPS, which iteratively couples multiple TPS with limited control points into a more flexible and powerful transformation. In light of the laborious annotation cost, we develop a semi-supervised learning scheme to improve warping quality by exploiting unlabeled data. Experiments demonstrate the superiority and universality of CoupledTPS over the existing state-of-the-art solutions for rotation correction.
  arXiv  Detail & Related papers  (2024-01-24T13:03:28Z)
• 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)
• PnP-DETR: Towards Efficient Visual Analysis with Transformers [146.55679348493587]
  Recently, DETR pioneered the solution vision tasks with transformers, it directly translates the image feature map into the object result. Recent transformer-based image recognition model andTT show consistent efficiency gain.
  arXiv  Detail & Related papers  (2021-09-15T01:10:30Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)

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.