CLIP-Guided Multi-Task Regression for Multi-View Plant Phenotyping
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917314064023552 |
|---|---|
| author | Warmers, Simon Zawish, Muhammad Dharejo, Fayaz Ali Davy, Steven Timofte, Radu |
| author_facet | Warmers, Simon Zawish, Muhammad Dharejo, Fayaz Ali Davy, Steven Timofte, Radu |
| contents | Modeling plant growth dynamics plays a central role in modern agricultural research. However, learning robust predictors from multi-view plant imagery remains challenging due to strong viewpoint redundancy and viewpoint-dependent appearance changes. We propose a level-aware vision language framework that jointly predicts plant age and leaf count using a single multi-task model built on CLIP embeddings. Our method aggregates rotational views into angle-invariant representations and conditions visual features on lightweight text priors encoding viewpoint level for stable prediction under incomplete or unordered inputs. On the GroMo25 benchmark, our approach reduces mean age MAE from 7.74 to 3.91 and mean leaf-count MAE from 5.52 to 3.08 compared to the GroMo baseline, corresponding to improvements of 49.5% and 44.2%, respectively. The unified formulation simplifies the pipeline by replacing the conventional dual-model setup while improving robustness to missing views. The models and code is available at: https://github.com/SimonWarmers/CLIP-MVP |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04091 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CLIP-Guided Multi-Task Regression for Multi-View Plant Phenotyping Warmers, Simon Zawish, Muhammad Dharejo, Fayaz Ali Davy, Steven Timofte, Radu Computer Vision and Pattern Recognition Modeling plant growth dynamics plays a central role in modern agricultural research. However, learning robust predictors from multi-view plant imagery remains challenging due to strong viewpoint redundancy and viewpoint-dependent appearance changes. We propose a level-aware vision language framework that jointly predicts plant age and leaf count using a single multi-task model built on CLIP embeddings. Our method aggregates rotational views into angle-invariant representations and conditions visual features on lightweight text priors encoding viewpoint level for stable prediction under incomplete or unordered inputs. On the GroMo25 benchmark, our approach reduces mean age MAE from 7.74 to 3.91 and mean leaf-count MAE from 5.52 to 3.08 compared to the GroMo baseline, corresponding to improvements of 49.5% and 44.2%, respectively. The unified formulation simplifies the pipeline by replacing the conventional dual-model setup while improving robustness to missing views. The models and code is available at: https://github.com/SimonWarmers/CLIP-MVP |
| title | CLIP-Guided Multi-Task Regression for Multi-View Plant Phenotyping |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.04091 |