Papers
arxiv:2610.10491

Insights from Autoresearch for Solar Panel Segmentation

Published on Oct 7
Authors:
,
,
,

Abstract

AutoResearch enables a coding language model to edit a fixed photovoltaic panel segmentation training program under a one-hour GPU budget, improving one-hour baselines but not transferring across hardware, with Qwen3-8B reaching 0.836 test IoU versus 0.833 for a GAN-augmented reference.

This paper investigates AutoResearch, a protocol in which a coding language model edits a training program under a one-hour GPU budget and retains a change only if validation IoU improves. The protocol is applied to photovoltaic panel segmentation on a frozen real-image split, with DeepLabV3--ResNet-50 held fixed. Three campaigns of 24 experiments, using Gemma~4 12B, Qwen3-8B all improve their one-hour baselines, but retained modifications do not transfer across hardware. The Qwen3-8B configuration, trained on real images only, reaches a test IoU of 0.836 versus 0.833 for the reference GAN-augmented schedule. Research repository https://github.com/VU-AIML/automl4eo-autoresearch-segmentation.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.10491 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.10491 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.10491 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.