Surgical fine-tuning for Grape Bunch Segmentation under Visual Domain Shifts
This work addresses robust visual perception for mobile robots in agriculture, but it is incremental as it applies an existing fine-tuning technique to a new task.
The paper tackles the problem of segmenting grape bunches from images collected by mobile robots in vineyards under visual domain shifts, and shows that surgical fine-tuning of specific model layers adapts pre-trained models to new data while reducing tuned parameters.
Mobile robots will play a crucial role in the transition towards sustainable agriculture. To autonomously and effectively monitor the state of plants, robots ought to be equipped with visual perception capabilities that are robust to the rapid changes that characterise agricultural settings. In this paper, we focus on the challenging task of segmenting grape bunches from images collected by mobile robots in vineyards. In this context, we present the first study that applies surgical fine-tuning to instance segmentation tasks. We show how selectively tuning only specific model layers can support the adaptation of pre-trained Deep Learning models to newly-collected grape images that introduce visual domain shifts, while also substantially reducing the number of tuned parameters.