# γ-Quant: Towards Learnable Quantization for Low-bit Pattern Recognition

arXiv: https://arxiv.org/abs/2509.22448 · HTML: https://mlsanity.com/paper/2509.22448/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 49 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Probabilistic Anchor Assignment with IoU Prediction for Object Detection](https://mlsanity.com/paper/2007.08103/) (2020)
- [Deep Optics for Monocular Depth Estimation and 3D Object Detection](https://mlsanity.com/paper/1904.08601/) (2019)
- [Dirty Pixels: Towards End-to-End Image Processing and Perception](https://mlsanity.com/paper/1701.06487/) (2017)
- [Reconfiguring the Imaging Pipeline for Computer Vision](https://mlsanity.com/paper/1705.04352/) (2017)
- [WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition](https://mlsanity.com/paper/2304.05088/) (2023)
- [GenISP: Neural ISP for Low-Light Machine Cognition](https://mlsanity.com/paper/2205.03688/) (2022)
- [AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection](https://mlsanity.com/paper/2410.22939/) (2024)
- [Differentiable Network Pruning for Microcontrollers](https://mlsanity.com/paper/2110.08350/) (2021)
- [Raw or Cooked? Object Detection on RAW Images](https://mlsanity.com/paper/2301.08965/) (2023)
- [Hang-Time HAR: A Benchmark Dataset for Basketball Activity Recognition using Wrist-Worn Inertial Sensors](https://mlsanity.com/paper/2305.13124/) (2023)
- [AHAR: Adaptive CNN for Energy-efficient Human Activity Recognition in Low-power Edge Devices](https://mlsanity.com/paper/2102.01875/) (2021)
- [Ultra-compact Binary Neural Networks for Human Activity Recognition on RISC-V Processors](https://mlsanity.com/paper/2205.12781/) (2022)
- [Physics vs. Learned Priors: Rethinking Camera and Algorithm Design for Task-Specific Imaging](https://mlsanity.com/paper/2204.09871/) (2022)
- [Human Activity Recognition on Microcontrollers with Quantized and Adaptive Deep Neural Networks](https://mlsanity.com/paper/2209.00839/) (2022)
- [Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters](https://mlsanity.com/paper/2304.14736/) (2023)
- [DISeR: Designing Imaging Systems with Reinforcement Learning](https://mlsanity.com/paper/2309.13851/) (2023)
- [A Learnable Color Correction Matrix for RAW Reconstruction](https://mlsanity.com/paper/2409.02497/) (2024)
- [Smartphone Sensor-based Human Activity Recognition Robust to Different Sampling Rates](https://mlsanity.com/paper/2101.00812/) (2021)

## Built on by (most cited first, 2 of 2)

- [RAWDet-7: A Multi-Scenario Benchmark for Object Detection and Description on Quantized RAW Images](https://mlsanity.com/paper/2602.03760/) (2026)
- [Failure or Drift? Evaluating Monocular SLAM under Synthetic and Real-World Corruptions](https://mlsanity.com/paper/2608.30690/) (2026)

## Abstract (arXiv)

Most pattern recognition models are developed on pre-proce-ssed data. In computer vision, for instance, RGB images processed through image signal processing (ISP) pipelines designed to cater to human perception are the most frequent input to image analysis networks. However, many modern vision tasks operate without a human in the loop, raising the question of whether such pre-processing is optimal for automated analysis. Similarly, human activity recognition (HAR) on body-worn sensor data commonly takes normalized floating-point data arising from a high-bit analog-to-digital converter (ADC) as an input, despite such an approach being highly inefficient in terms of data transmission, significantly affecting the battery life of wearable devices. In this work, we target low-bandwidth and energy-constrained settings where sensors are limited to low-bit-depth capture. We propose γ-Quant, i.e.~the task-specific learning of a non-linear quantization for pattern recognition. We exemplify our approach on raw-image object detection as well as HAR of wearable data, and demonstrate that raw data with a learnable quantization using as few as 4-bits can perform on par with the use of raw 12-bit data. All code to reproduce our experiments is publicly available via https://github.com/Mishalfatima/Gamma-Quant