Saved in:
Bibliographic Details
Main Authors: Týbl, Ondřej, Neumann, Lukáš
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.06035
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909829742723072
author Týbl, Ondřej
Neumann, Lukáš
author_facet Týbl, Ondřej
Neumann, Lukáš
contents We introduce Universal Neural Architecture Space (UniNAS), a generic search space for neural architecture search (NAS) which unifies convolutional networks, transformers, and their hybrid architectures under a single, flexible framework. Our approach enables discovery of novel architectures as well as analyzing existing architectures in a common framework. We also propose a new search algorithm that allows traversing the proposed search space, and demonstrate that the space contains interesting architectures, which, when using identical training setup, outperform state-of-the-art hand-crafted architectures. Finally, a unified toolkit including a standardized training and evaluation protocol is introduced to foster reproducibility and enable fair comparison in NAS research. Overall, this work opens a pathway towards systematically exploring the full spectrum of neural architectures with a unified graph-based NAS perspective.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06035
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Universal Neural Architecture Space: Covering ConvNets, Transformers and Everything in Between
Týbl, Ondřej
Neumann, Lukáš
Computer Vision and Pattern Recognition
We introduce Universal Neural Architecture Space (UniNAS), a generic search space for neural architecture search (NAS) which unifies convolutional networks, transformers, and their hybrid architectures under a single, flexible framework. Our approach enables discovery of novel architectures as well as analyzing existing architectures in a common framework. We also propose a new search algorithm that allows traversing the proposed search space, and demonstrate that the space contains interesting architectures, which, when using identical training setup, outperform state-of-the-art hand-crafted architectures. Finally, a unified toolkit including a standardized training and evaluation protocol is introduced to foster reproducibility and enable fair comparison in NAS research. Overall, this work opens a pathway towards systematically exploring the full spectrum of neural architectures with a unified graph-based NAS perspective.
title Universal Neural Architecture Space: Covering ConvNets, Transformers and Everything in Between
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.06035