Skip to main contentSearchSubmitDonateLog in

Search arXiv

Press Enter to search · Advanced search

Computer Science > Computer Vision and Pattern Recognition

arXiv:2608.07984 (cs)

[Submitted on 8 Aug 2026]

Title:AgriField-40K: Adapting Vision Models to Agriculture With Efficient Continual Pretraining

Authors:Vasileios Tzouras, Paraskevas Pegios, Lazaros Nalpantidis

View a PDF of the paper titled AgriField-40K: Adapting Vision Models to Agriculture With Efficient Continual Pretraining, by Vasileios Tzouras and 2 other authors

View PDFHTML (experimental)

Abstract:Field-based agricultural computer vision is important for precision agriculture, yet it largely depends on expensive annotations and costly adaptation of large pretrained models. We introduce AgriField-40K, a field-centric dataset curated from 17 public resources and covering diverse crops, weeds, and field conditions. Building on this, we present AgriMAE, a parameter-efficient continual pretraining baseline that adapts a masked autoencoder pretrained on natural images by training only lightweight adapters. We further explore semantic feature reconstruction as an alternative pretraining objective and evaluate transfer across multiple tasks. AgriMAE consistently improves downstream performance and can match or even outperform full fine-tuning while using up to $9\times$ fewer trainable parameters, showing that AgriField-40K is a practical resource for continual pretraining in agricultural vision. Project page: this https URL

Comments:Accepted at the Computer Vision in Plant Phenotyping and Agriculture (CVPPA) Workshop at the European Conference on Computer Vision (ECCV) 2026
Subjects:Computer Vision and Pattern Recognition (cs.CV)
Cite as:arXiv:2608.07984 [cs.CV]
(or arXiv:2608.07984v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.07984

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Vasileios Tzouras [view email]

[v1] Sat, 8 Aug 2026 07:38:01 UTC (24,651 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled AgriField-40K: Adapting Vision Models to Agriculture With Efficient Continual Pretraining, by Vasileios Tzouras and 2 other authors

• View PDF
• HTML (experimental)
• TeX Source

view license

Current browse context:

cs.CV

<prev | next>

new | recent | 2026-08

Change to browse by:

cs

References & Citations

• NASA ADS
• Google Scholar
• Semantic Scholar

export BibTeX citation Loading...

BibTeX formatted citation

×

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

• [x] Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

• [x] Connected Papers Toggle

Connected Papers (What is Connected Papers?)

• [x] Litmaps Toggle

Litmaps (What is Litmaps?)

• [x] scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

• [x] alphaXiv Toggle

alphaXiv (What is alphaXiv?)

• [x] Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

• [x] DagsHub Toggle

DagsHub (What is DagsHub?)

• [x] GotitPub Toggle

Gotit.pub (What is GotitPub?)

• [x] Huggingface Toggle

Hugging Face (What is Huggingface?)

• [x] ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

• [x] Replicate Toggle

Replicate (What is Replicate?)

• [x] Spaces Toggle

Hugging Face Spaces (What is Spaces?)

• [x] Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

• [x] Link to Influence Flower

Influence Flower (What are Influence Flowers?)

• [x] Core recommender toggle

CORE Recommender (What is CORE?)

• Author
• Venue
• Institution
• Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | [Disable MathJax](javascript:setMathjaxCookie()) (What is MathJax?)

We gratefully acknowledge support from our major funders, member institutions, , and all contributors.

About·Help·Contact·Subscribe·Copyright·Privacy·Accessibility·Operational Status (opens in new tab)

Major funding support from