用CLIP统一预测植物年龄和叶片数，提升多视角图像分析鲁棒性。
CLIP-Guided Multi-Task Regression for Multi-View Plant Phenotyping
- 基于CLIP嵌入构建多任务模型，融合旋转视角的不变特征。
- 在GroMo25上年龄误差降49.5%，叶片数误差降44.2%。
- 适合处理缺失或无序视角的植物表型数据，简化传统双模型流程。
建模植物生长动态在现代农业研究中至关重要。然而，由于视角冗余和视角相关的外观变化，从多视角植物图像中学习鲁棒预测器仍具挑战。我们提出一种层级感知的视觉语言框架，利用单个多任务模型联合预测植物年龄与叶数，该模型基于CLIP嵌入构建。方法将旋转视角聚合为角度无关表示，并以轻量级文本先验条件化视觉特征，编码视角层级信息，实现对不完整或无序输入的稳定预测。在GroMo25基准上，相比GroMo基线，平均年龄MAE从7.74降至3.91（改善49.5%），平均叶数MAE从5.52降至3.08（改善44.2%）。统一建模简化了流程，替代传统的双模型设置，同时提升对缺失视角的鲁棒性。代码与模型见：https://github.com/SimonWarmers/CLIP-MVP
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。