3 papers
cs.CV2026
How Merge-Tolerant Are Vision Transformers for Wheat Phenotyping?
Simon Ravé, Pejman Rasti, David Rousseau
Vision-based wheat phenotyping requires repeated measurements under deployment constraints, from growth-stage recognition to wheat-head counting and organ segmentation. Plain Visio…
cs.CV2026
MPM: Mutual Pair Merging for Efficient Vision Transformers
Simon Ravé, Pejman Rasti, David Rousseau
Decreasing sequence length is a common way to accelerate transformers, but prior token reduction work often targets classification and reports proxy metrics rather than end-to-end…
cs.CV2025
Unlocking Zero-Shot Plant Segmentation with Pl@ntNet Intelligence
Simon Ravé, Jean-Christophe Lombardo, Pejman Rasti +2
We present a zero-shot segmentation approach for agricultural imagery that leverages Plantnet, a large-scale plant classification model, in conjunction with its DinoV2 backbone and…