TeTRA-VPR: A Ternary Transformer Approach for Compact Visual Place Recognition

• URL: http://arxiv.org/abs/2503.02511v1
• Date: Tue, 04 Mar 2025 11:20:10 GMT
• Title: TeTRA-VPR: A Ternary Transformer Approach for Compact Visual Place Recognition
• Abstract summary: We propose TeTRA, a ternary transformer approach that progressively quantizes the ViT backbone to 2-bit precision and binarizes its final embedding layer.<n> Experiments on standard VPR benchmarks demonstrate that TeTRA reduces memory consumption by up to 69% compared to efficient baselines.<n>These gains enable high-accuracy VPR on power-constrained, memory-limited robotic platforms, making TeTRA an appealing solution for real-world deployment.
• Score: 24.433604332415204
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual Place Recognition (VPR) localizes a query image by matching it against a database of geo-tagged reference images, making it essential for navigation and mapping in robotics. Although Vision Transformer (ViT) solutions deliver high accuracy, their large models often exceed the memory and compute budgets of resource-constrained platforms such as drones and mobile robots. To address this issue, we propose TeTRA, a ternary transformer approach that progressively quantizes the ViT backbone to 2-bit precision and binarizes its final embedding layer, offering substantial reductions in model size and latency. A carefully designed progressive distillation strategy preserves the representational power of a full-precision teacher, allowing TeTRA to retain or even surpass the accuracy of uncompressed convolutional counterparts, despite using fewer resources. Experiments on standard VPR benchmarks demonstrate that TeTRA reduces memory consumption by up to 69% compared to efficient baselines, while lowering inference latency by 35%, with either no loss or a slight improvement in recall@1. These gains enable high-accuracy VPR on power-constrained, memory-limited robotic platforms, making TeTRA an appealing solution for real-world deployment.

Related papers

• Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications [99.72917069918485]
  We propose a novel sparse model inversion strategy to speed up existing dense inversion methods.<n>Specifically, we invert semantic foregrounds while stopping the inversion of noisy backgrounds and potential spurious correlations.
  arXiv  Detail & Related papers  (2025-10-31T05:14:36Z)
• Flexible and Efficient Spatio-Temporal Transformer for Sequential Visual Place Recognition [8.050179481110222]
  We show that Adapt-STformer boosts recall by up to 17% while reducing sequence extraction time by 36% and lowering memory usage by 35%.<n>Experiments on the Nordland, Oxford, and NuScenes datasets show that Adapt-STformer boosts recall by up to 17% while reducing sequence extraction time by 36% and lowering memory usage by 35%.
  arXiv  Detail & Related papers  (2025-10-05T16:52:12Z)
• Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy [5.699098817569033]
  This paper introduces an activation-aware model compression methodology that uses selective low-rank weight tensor approximations of different layers to reduce the parameter count of ViTs. The presented method significantly reduces the parameter count of DeiT-B by 60% with less than 1% accuracy drop on the ImageNet dataset. In addition to this, the presented compression technique can compress large DeiT/ViT models to have about the same model size as smaller DeiT/ViT variants while yielding up to 1.8% accuracy gain.
  arXiv  Detail & Related papers  (2024-02-08T19:01:14Z)
• Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation [73.31524865643709]
  We present a plug-and-play pruning-and-recovering framework, called Hourglass Tokenizer (HoT), for efficient transformer-based 3D pose estimation from videos. Our HoDT begins with pruning pose tokens of redundant frames and ends with recovering full-length tokens, resulting in a few pose tokens in the intermediate transformer blocks. Our method can achieve both high efficiency and estimation accuracy compared to the original VPT models.
  arXiv  Detail & Related papers  (2023-11-20T18:59:51Z)
• VST++: Efficient and Stronger Visual Saliency Transformer [74.26078624363274]
  We develop an efficient and stronger VST++ model to explore global long-range dependencies. We evaluate our model across various transformer-based backbones on RGB, RGB-D, and RGB-T SOD benchmark datasets.
  arXiv  Detail & Related papers  (2023-10-18T05:44:49Z)
• Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer [56.87383229709899]
  We develop an information rectification module (IRM) and a distribution guided distillation scheme for fully quantized vision transformers (Q-ViT) Our method achieves a much better performance than the prior arts.
  arXiv  Detail & Related papers  (2022-10-13T04:00:29Z)
• Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning [138.29273453811945]
  Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks. We propose a new Wavelet Vision Transformer (textbfWave-ViT) that formulates the invertible down-sampling with wavelet transforms and self-attention learning.
  arXiv  Detail & Related papers  (2022-07-11T16:03:51Z)
• Efficient Decoder-free Object Detection with Transformers [75.00499377197475]
  Vision transformers (ViTs) are changing the landscape of object detection approaches. We propose a decoder-free fully transformer-based (DFFT) object detector. DFFT_SMALL achieves high efficiency in both training and inference stages.
  arXiv  Detail & Related papers  (2022-06-14T13:22:19Z)
• AdaViT: Adaptive Tokens for Efficient Vision Transformer [91.88404546243113]
  We introduce AdaViT, a method that adaptively adjusts the inference cost of vision transformer (ViT) for images of different complexity. AdaViT achieves this by automatically reducing the number of tokens in vision transformers that are processed in the network as inference proceeds.
  arXiv  Detail & Related papers  (2021-12-14T18:56:07Z)
• HRFormer: High-Resolution Transformer for Dense Prediction [99.6060997466614]
  We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks. We take advantage of the multi-resolution parallel design introduced in high-resolution convolutional networks (HRNet) We demonstrate the effectiveness of the High-Resolution Transformer on both human pose estimation and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2021-10-18T15:37:58Z)

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.