Skip to content
Back to skills

Enhancing Onceforall A Study On Parallel Blocks Skip Connections And Early Exits

ASecurity

**arXiv ID:** 2302.01888 **Authors:** Simone Sarti, Eugenio Lomurno, Andrea Falanti, Matteo Matteucci **Published:** 2023-02-03T17:53:40Z **Abstract:** The use of Neural Architecture Search (NAS) techniques to automate the design of neural networks has become increasingly popular in recent years. The proliferation of devices with different hardware characteristics using such neural networks, as well as the need to reduce the power consumption for their search, has led to the realisation of On...

  • 3 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 11, 2026
toolsgoperformance

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill enhancing-onceforall-a-study-on-parallel-blocks-skip-connections-and-early-exits --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Enhancing Onceforall A Study On Parallel Blocks Skip Connections And Early Exits?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Enhancing Onceforall A Study On Parallel Blocks Skip Connections And Early Exits
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-enhancing-onceforall-a-study-on-parallel-blocks-sk/badge)](https://www.skillsdirectory.com/skills/hiyenwong-enhancing-onceforall-a-study-on-parallel-blocks-sk)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Enhancing Once-For-All: A Study on Parallel Blocks, Skip Connections and Early Exits

**arXiv ID:** 2302.01888
**Authors:** Simone Sarti, Eugenio Lomurno, Andrea Falanti, Matteo Matteucci
**Published:** 2023-02-03T17:53:40Z
**Abstract:**
The use of Neural Architecture Search (NAS) techniques to automate the design of neural networks has become increasingly popular in recent years. The proliferation of devices with different hardware characteristics using such neural networks, as well as the need to reduce the power consumption for their search, has led to the realisation of Once-For-All (OFA), an eco-friendly algorithm characterised by the ability to generate easily adaptable models through a single learning process. In order to improve this paradigm and develop high-performance yet eco-friendly NAS techniques, this paper presents OFAv2, the extension of OFA aimed at improving its performance while maintaining the same ecological advantage. The algorithm is improved from an architectural point of view by including early exits, parallel blocks and dense skip connections. The training process is extended by two new phases called Elastic Level and Elastic Height. A new Knowledge Distillation technique is presented to handle multi-output networks, and finally a new strategy for dynamic teacher network selection is proposed. These modifications allow OFAv2 to improve its accuracy performance on the Tiny ImageNet dataset by up to 12.07% compared to the original version of OFA, while maintaining the algorithm flexibility and advantages.

## Skill Description

This skill is generated from the arXiv paper: Enhancing Once-For-All: A Study on Parallel Blocks, Skip Connections and Early Exits (2302.01888).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2302.01888](http://arxiv.org/abs/2302.01888v1)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.