用二值化Transformer实现轻量级视觉定位，精度不降反升。
TeTRA-VPR: A Ternary Transformer Approach for Compact Visual Place Recognition
- 分步量化ViT到2比特，再二值化嵌入层，大幅压缩模型
- 在标准数据集上内存减少69%，推理延迟降低35%，召回率不变或略升
- 适合无人机、移动机器人等资源受限设备部署
视觉定位（VPR）通过匹配查询图像与地理标记的参考图像数据库来实现位置识别，对机器人导航与建图至关重要。尽管视觉变压器（ViT）性能优越，但其庞大模型常超出无人机和移动机器人等资源受限平台的内存与计算预算。为此，我们提出TeTRA，一种逐级量化ViT骨干至2比特并二值化最终嵌入层的三值变换器方法，显著降低模型尺寸与延迟。精心设计的渐进式知识蒸馏策略保留了全精度教师模型的表征能力，使TeTRA在资源更少的情况下仍能保持甚至超越未压缩卷积模型的精度。标准VPR基准测试表明，相比高效基线，TeTRA内存消耗最多减少69%，推理延迟降低35%，召回率@1无损失或略有提升。这些优势使其可在功耗与内存受限的机器人平台上实现高精度VPR，为实际部署提供理想方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。