Point-JEPAによるラベル効率的な把持関節角度予測
Label-Efficient Grasp Joint Prediction with Point-JEPA
Point-JEPAで事前学習した3D点群エンコーダを使い、少ないラベルで多指ハンドの把持関節角度を予測する手法を検証した。低ラベル設定で精度が向上し、全教師ありと同等の性能に達した。
著者: Jed Guzelkabaagac, Boris Petrović
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
We study whether 3D self-supervised pretraining with Point--JEPA enables label-efficient grasp joint-angle prediction. Meshes are sampled to point clouds and tokenized; a ShapeNet-pretrained Point--JEPA encoder feeds a $K{=}5$ multi-hypothesis head trained with winner-takes-all and evaluated by top--logit selection. On a multi-finger hand dataset with strict object-level splits, Point--JEPA improves top--logit RMSE and Coverage@15$^{\circ}$ in low-label regimes (e.g., 26% lower RMSE at 25% data) and reaches parity at full supervision, suggesting JEPA-style pretraining is a practical lever for data-efficient grasp learning.