mlsanityData to 14 Oct 2026

TAT-VPR: Ternary Adaptive Transformer for Dynamic and Efficient Visual Place Recognition

arXiv 2505.16447 ↗First posted 22 May 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

TAT-VPR is a ternary-quantized transformer that brings dynamic accuracy-efficiency trade-offs to visual SLAM loop-closure. By fusing ternary weights with a learned activation-sparsity gate, the model can control computation by up to 40% at run-time without degrading performance (Recall@1). The proposed two-stage distillation pipeline preserves descriptor quality, letting it run on micro-UAV and embedded SLAM stacks while matching state-of-the-art localization accuracy.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 14 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

13 of 14 references.

References · 13

  1. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
  2. 2019Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mappingcited by 184
  3. 2022Rethinking Visual Geo-localization for Large-Scale Applicationscited by 163
  4. 2023AnyLoc: Towards Universal Visual Place Recognitioncited by 163
  5. 2023MixVPR: Feature Mixing for Visual Place Recognitioncited by 161
  6. 2023Optimal Transport Aggregation for Visual Place Recognitioncited by 152
  7. 2023EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognitioncited by 111
  8. 2022GSV-Cities: Toward Appropriate Supervised Visual Place Recognitioncited by 93
  9. 2024BoQ: A Place is Worth a Bag of Learnable Queriescited by 64
  10. 2024Q-Sparse: All Large Language Models can be Fully Sparsely-Activatedcited by 25
  11. 2020Binary Neural Networks for Memory-Efficient and Effective Visual Place Recognition in Changing Environmentscited by 16
  12. 2024BitNet a4.8: 4-bit Activations for 1-bit LLMscited by 16
1 more
  1. 2023Design Space Exploration of Low-Bit Quantized Neural Networks for Visual Place Recognitioncited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025TeTRA-VPR: A Ternary Transformer Approach for Compact Visual Place Recognition
  2. 2022TerViT: An Efficient Ternary Vision Transformer
  3. 2026FTerViT: Fully Ternary Vision Transformer
  4. 2024ViT-1.58b: Mobile Vision Transformers in the 1-bit Era
  5. 2023Compressing Vision Transformers for Low-Resource Visual Learning
  6. 2026QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer
  7. 2023BPT: Binary Point Cloud Transformer for Place Recognition
  8. 2024AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer