Show and Grasp: Few-shot Semantic Segmentation for Robot Grasping through Zero-shot Foundation Models

TL;DR

This paper introduces a novel approach combining foundation models with a few-shot classifier to enhance robot grasping, significantly improving segmentation and grasping accuracy with minimal examples.

Contribution

It proposes a new method that leverages foundation models and a high-performing few-shot classifier for better generalization in robot grasping tasks.

Findings

Improves few-shot semantic segmentation accuracy (+10.5% mIoU)

Enhances real-world grasp synthesis (+21.7% grasp accuracy)

Outperforms existing methods on benchmark datasets

Abstract

The ability of a robot to pick an object, known as robot grasping, is crucial for several applications, such as assembly or sorting. In such tasks, selecting the right target to pick is as essential as inferring a correct configuration of the gripper. A common solution to this problem relies on semantic segmentation models, which often show poor generalization to unseen objects and require considerable time and massive data to be trained. To reduce the need for large datasets, some grasping pipelines exploit few-shot semantic segmentation models, which are capable of recognizing new classes given a few examples. However, this often comes at the cost of limited performance and fine-tuning is required to be effective in robot grasping scenarios. In this work, we propose to overcome all these limitations by combining the impressive generalization capability reached by foundation models with a high-performing few-shot classifier, working as a score function to select the segmentation that is closer to the support set. The proposed model is designed to be embedded in a grasp synthesis pipeline. The extensive experiments using one or five examples show that our novel approach overcomes existing performance limitations, improving the state of the art both in few-shot semantic segmentation on the Graspnet-1B (+10.5% mIoU) and Ocid-grasp (+1.6% AP) datasets, and real-world few-shot grasp synthesis (+21.7% grasp accuracy). The project page is available at: https://leobarcellona.github.io/showandgrasp.github.io/