End-to-end fully-binarized network design: from Generic Learned Thermometer to Block Pruning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nguyen, Thien, Guicquero, William
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910954887839744
author Nguyen, Thien
Guicquero, William
author_facet Nguyen, Thien
Guicquero, William
contents Existing works on Binary Neural Network (BNN) mainly focus on model's weights and activations while discarding considerations on the input raw data. This article introduces Generic Learned Thermometer (GLT), an encoding technique to improve input data representation for BNN, relying on learning non linear quantization thresholds. This technique consists in multiple data binarizations which can advantageously replace a conventional Analog to Digital Conversion (ADC) that uses natural binary coding. Additionally, we jointly propose a compact topology with light-weight grouped convolutions being trained thanks to block pruning and Knowledge Distillation (KD), aiming at reducing furthermore the model size so as its computational complexity. We show that GLT brings versatility to the BNN by intrinsically performing global tone mapping, enabling significant accuracy gains in practice (demonstrated by simulations on the STL-10 and VWW datasets). Moreover, when combining GLT with our proposed block-pruning technique, we successfully achieve lightweight (under 1Mb), fully-binarized models with limited accuracy degradation while being suitable for in-sensor always-on inference use cases.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13462
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle End-to-end fully-binarized network design: from Generic Learned Thermometer to Block Pruning
Nguyen, Thien
Guicquero, William
Machine Learning
Hardware Architecture
Computer Vision and Pattern Recognition
Image and Video Processing
Existing works on Binary Neural Network (BNN) mainly focus on model's weights and activations while discarding considerations on the input raw data. This article introduces Generic Learned Thermometer (GLT), an encoding technique to improve input data representation for BNN, relying on learning non linear quantization thresholds. This technique consists in multiple data binarizations which can advantageously replace a conventional Analog to Digital Conversion (ADC) that uses natural binary coding. Additionally, we jointly propose a compact topology with light-weight grouped convolutions being trained thanks to block pruning and Knowledge Distillation (KD), aiming at reducing furthermore the model size so as its computational complexity. We show that GLT brings versatility to the BNN by intrinsically performing global tone mapping, enabling significant accuracy gains in practice (demonstrated by simulations on the STL-10 and VWW datasets). Moreover, when combining GLT with our proposed block-pruning technique, we successfully achieve lightweight (under 1Mb), fully-binarized models with limited accuracy degradation while being suitable for in-sensor always-on inference use cases.
title End-to-end fully-binarized network design: from Generic Learned Thermometer to Block Pruning
topic Machine Learning
Hardware Architecture
Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2505.13462