paper-with-me

Papers

SPROUT: A Scalable Diffusion Foundation Model for Agricultural Vision

2026-03-29 · Shuai Xiang, Wei Guo, James Burridge, Shouyang Liu, Hao Lu, Tokihiro Fukatsu arxiv

Image-based plant phenotyping depends on dense structural understanding of crops, yet pixel-level annotation remains expensive across species, organs, growth stages, and field conditions. General-purpose vision foundation models offer a natural route to label efficiency, but their web-scale pretraining objectives transfer weakly to agricultural imagery, where semantics are often determined by fine organ geometry inside repetitive, texture-dominated scenes. We introduce SPROUT, a diffusion foundation model for multi-crop plant phenotyping. SPROUT learns from 2.6~million unlabeled open-field images using a VAE-free pixel-space Diffusion Transformer, and selects transferable features with a label-free effective-rank criterion over denoising timesteps. This design shifts pretraining from crop-based invariance to structure-preserving denoising, making the representation better aligned with dense phenotyping tasks. We evaluate SPROUT across dense phenotyping tasks, including organ segmentation, crop-weed parsing, depth estimation, and counting. SPROUT consistently improves over strong web-pretrained baselines, with the largest gains on dense structural prediction, and shows favorable label and compute efficiency compared with general-purpose and crop-specific foundation models.

📄 PDF Abstract BibTeX arXiv:2603.27519

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Supervise Less, See More: Training-free Nuclear Instance Segmentation with Prototype-Guided Prompting

2025-11-25 · Wen Zhang, Qin Ren, Wenjing Liu, Haibin Ling 외 arxiv

Accurate nuclear instance segmentation is a pivotal task in computational pathology, supporting data-driven clinical insights and facilitating downstream translational applications. While large vision foundation models h…

Instance Segmentation

SPROUT: Self-Progressing Robust Training

2019-09-25 · Minhao Cheng, Pin-Yu Chen, Sijia Liu, Shiyu Chang 외

Enhancing model robustness under new and even adversarial environments is a crucial milestone toward building trustworthy and reliable machine learning systems. Current robust training methods such as adversarial trainin…

Adversarial Robustness

Self-Progressing Robust Training

2020-12-22 · Minhao Cheng, Pin-Yu Chen, Sijia Liu, Shiyu Chang 외

Enhancing model robustness under new and even adversarial environments is a crucial milestone toward building trustworthy machine learning systems. Current robust training methods such as adversarial training explicitly …

Adversarial Robustness

Quality Detection of Stored Potatoes via Transfer Learning: A CNN and Vision Transformer Approach

2026-01-02 · Shrikant Kapse, Priyankkumar Dhrangdhariya, Priya Kedia, Manasi Patwardhan 외 arxiv

Image-based deep learning provides a non-invasive, scalable solution for monitoring potato quality during storage, addressing key challenges such as sprout detection, weight loss estimation, and shelf-life prediction. In…

Transfer Learning

Foundation Models Meet Agriculture: Challenges Beyond Pretraining

2026-08-31 · Vishal Nedungadi, Xingguo Xiong, Marc Rußwurm, Ioannis N. Athanasiadis arxiv

Global food security and sustainable climate action increasingly rely on robust, scalable agricultural monitoring. Earth observation foundation models have emerged as powerful, label-efficient tools across general remote…

Crop Classification