Uncertainty-Aware Decomposed Hybrid Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ditzel, Sina, Jaziri, Achref, Pliushch, Iuliia, Ramesh, Visvanathan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915212935823360
author Ditzel, Sina
Jaziri, Achref
Pliushch, Iuliia
Ramesh, Visvanathan
author_facet Ditzel, Sina
Jaziri, Achref
Pliushch, Iuliia
Ramesh, Visvanathan
contents The robustness of image recognition algorithms remains a critical challenge, as current models often depend on large quantities of labeled data. In this paper, we propose a hybrid approach that combines the adaptability of neural networks with the interpretability, transparency, and robustness of domain-specific quasi-invariant operators. Our method decomposes the recognition into multiple task-specific operators that focus on different characteristics, supported by a novel confidence measurement tailored to these operators. This measurement enables the network to prioritize reliable features and accounts for noise. We argue that our design enhances transparency and robustness, leading to improved performance, particularly in low-data regimes. Experimental results in traffic sign detection highlight the effectiveness of the proposed method, especially in semi-supervised and unsupervised scenarios, underscoring its potential for data-constrained applications.
format Preprint
id arxiv_https___arxiv_org_abs_2503_19096
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty-Aware Decomposed Hybrid Networks
Ditzel, Sina
Jaziri, Achref
Pliushch, Iuliia
Ramesh, Visvanathan
Computer Vision and Pattern Recognition
Machine Learning
The robustness of image recognition algorithms remains a critical challenge, as current models often depend on large quantities of labeled data. In this paper, we propose a hybrid approach that combines the adaptability of neural networks with the interpretability, transparency, and robustness of domain-specific quasi-invariant operators. Our method decomposes the recognition into multiple task-specific operators that focus on different characteristics, supported by a novel confidence measurement tailored to these operators. This measurement enables the network to prioritize reliable features and accounts for noise. We argue that our design enhances transparency and robustness, leading to improved performance, particularly in low-data regimes. Experimental results in traffic sign detection highlight the effectiveness of the proposed method, especially in semi-supervised and unsupervised scenarios, underscoring its potential for data-constrained applications.
title Uncertainty-Aware Decomposed Hybrid Networks
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2503.19096