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

• URL: http://arxiv.org/abs/2509.22448v1
• Date: Fri, 26 Sep 2025 15:03:55 GMT
• Title: $γ$-Quant: Towards Learnable Quantization for Low-bit Pattern Recognition
• Authors: Mishal Fatima, Shashank Agnihotri, Marius Bock, Kanchana Vaishnavi Gandikota, Kristof Van Laerhoven, Michael Moeller, Margret Keuper,
• Abstract summary: We propose $gamma$-Quant, i.e., the task-specific learning of a non-linear quantization for pattern recognition.<n>We 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.
• Score: 28.31494154592102
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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 $\gamma$-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

Related papers

• MARMOT: Masked Autoencoder for Modeling Transient Imaging [30.865812827455326]
  We present a masked autoencoder for modeling transient imaging, or MARMOT, to facilitate non-line-of-sight (NLOS) applications.<n>Our MARMOT is a self-supervised model pretrianed on massive and diverse NLOS transient datasets.
  arXiv  Detail & Related papers  (2025-06-10T05:49:22Z)
• Quanv4EO: Empowering Earth Observation by means of Quanvolutional Neural Networks [62.12107686529827]
  This article highlights a significant shift towards leveraging quantum computing techniques in processing large volumes of remote sensing data. The proposed Quanv4EO model introduces a quanvolution method for preprocessing multi-dimensional EO data. Key findings suggest that the proposed model not only maintains high precision in image classification but also shows improvements of around 5% in EO use cases.
  arXiv  Detail & Related papers  (2024-07-24T09:11:34Z)
• Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery [78.43828998065071]
  Recent advances in unsupervised learning have demonstrated the ability of large vision models to achieve promising results on downstream tasks. Such pre-training techniques have also been explored recently in the remote sensing domain due to the availability of large amount of unlabelled data. In this paper, we re-visit transformers pre-training and leverage multi-scale information that is effectively utilized with multiple modalities.
  arXiv  Detail & Related papers  (2024-03-08T16:18:04Z)
• Let's Roll: Synthetic Dataset Analysis for Pedestrian Detection Across Different Shutter Types [7.0441427250832644]
  This paper studies the impact of different shutter mechanisms on machine learning (ML) object detection models on a synthetic dataset. In particular, we train and evaluate mainstream detection models with our synthetically-generated paired GS and RS datasets.
  arXiv  Detail & Related papers  (2023-09-15T04:07:42Z)
• Enabling ISP-less Low-Power Computer Vision [4.102254385058941]
  We release the raw version of a large-scale benchmark for generic high-level vision tasks. For ISP-less CV systems, training on raw images result in a 7.1% increase in test accuracy. We propose an energy-efficient form of analog in-pixel demosaicing that may be coupled with in-pixel CNN computations.
  arXiv  Detail & Related papers  (2022-10-11T13:47:30Z)
• GenISP: Neural ISP for Low-Light Machine Cognition [19.444297600977546]
  In low-light conditions, object detectors using raw image data are more robust than detectors using image data processed by an ISP pipeline. We propose a minimal neural ISP pipeline for machine cognition, named GenISP, that explicitly incorporates Color Space Transformation to a device-independent color space.
  arXiv  Detail & Related papers  (2022-05-07T17:17:24Z)
• Model-Based Image Signal Processors via Learnable Dictionaries [6.766416093990318]
  Digital cameras transform sensor RAW readings into RGB images by means of their Image Signal Processor (ISP) Recent approaches have attempted to bridge this gap by estimating the RGB to RAW mapping. We present a novel hybrid model-based and data-driven ISP that is both learnable and interpretable.
  arXiv  Detail & Related papers  (2022-01-10T08:36:10Z)
• SignalNet: A Low Resolution Sinusoid Decomposition and Estimation Network [79.04274563889548]
  We propose SignalNet, a neural network architecture that detects the number of sinusoids and estimates their parameters from quantized in-phase and quadrature samples. We introduce a worst-case learning threshold for comparing the results of our network relative to the underlying data distributions. In simulation, we find that our algorithm is always able to surpass the threshold for three-bit data but often cannot exceed the threshold for one-bit data.
  arXiv  Detail & Related papers  (2021-06-10T04:21:20Z)
• CNNs for JPEGs: A Study in Computational Cost [49.97673761305336]
  Convolutional neural networks (CNNs) have achieved astonishing advances over the past decade. CNNs are capable of learning robust representations of the data directly from the RGB pixels. Deep learning methods capable of learning directly from the compressed domain have been gaining attention in recent years.
  arXiv  Detail & Related papers  (2020-12-26T15:00:10Z)
• Deep traffic light detection by overlaying synthetic context on arbitrary natural images [49.592798832978296]
  We propose a method to generate artificial traffic-related training data for deep traffic light detectors. This data is generated using basic non-realistic computer graphics to blend fake traffic scenes on top of arbitrary image backgrounds. It also tackles the intrinsic data imbalance problem in traffic light datasets, caused mainly by the low amount of samples of the yellow state.
  arXiv  Detail & Related papers  (2020-11-07T19:57:22Z)
• Learning Camera Miscalibration Detection [83.38916296044394]
  This paper focuses on a data-driven approach to learn the detection of miscalibration in vision sensors, specifically RGB cameras. Our contributions include a proposed miscalibration metric for RGB cameras and a novel semi-synthetic dataset generation pipeline based on this metric. By training a deep convolutional neural network, we demonstrate the effectiveness of our pipeline to identify whether a recalibration of the camera's intrinsic parameters is required or not.
  arXiv  Detail & Related papers  (2020-05-24T10:32:49Z)

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.