# Sensor Calibration Model Balancing Accuracy, Real-time, and Efficiency

arXiv: https://arxiv.org/abs/2511.06715 · HTML: https://mlsanity.com/paper/2511.06715/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Builds on (most cited first, 8 of 8)

- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm](https://mlsanity.com/paper/1808.00278/) (2018)
- [EcoFormer: Energy-Saving Attention with Linear Complexity](https://mlsanity.com/paper/2209.09004/) (2022)
- [DeepRT: A Soft Real Time Scheduler for Computer Vision Applications on the Edge](https://mlsanity.com/paper/2105.01803/) (2021)
- [Enhancing Masked Time-Series Modeling via Dropping Patches](https://mlsanity.com/paper/2412.15315/) (2024)
- [Real-time Calibration Model for Low-cost Sensor in Fine-grained Time series](https://mlsanity.com/paper/2412.20170/) (2024)

## Abstract (arXiv)

Most on-device sensor calibration studies benchmark models only against three macroscopic requirements (i.e., accuracy, real-time, and resource efficiency), thereby hiding deployment bottlenecks such as instantaneous error and worst-case latency. We therefore decompose this triad into eight microscopic requirements and introduce Scare (Sensor Calibration model balancing Accuracy, Real-time, and Efficiency), an ultra-compressed transformer that fulfills them all. SCARE comprises three core components: (1) Sequence Lens Projector (SLP) that logarithmically compresses time-series data while preserving boundary information across bins, (2) Efficient Bitwise Attention (EBA) module that replaces costly multiplications with bitwise operations via binary hash codes, and (3) Hash optimization strategy that ensures stable training without auxiliary loss terms. Together, these components minimize computational overhead while maintaining high accuracy and compatibility with microcontroller units (MCUs). Extensive experiments on large-scale air-quality datasets and real microcontroller deployments demonstrate that Scare outperforms existing linear, hybrid, and deep-learning baselines, making Scare, to the best of our knowledge, the first model to meet all eight microscopic requirements simultaneously.