日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

セグメンテーションarXiv:2409.15481

未見物体インスタンスセグメンテーションへのSegment Anything Modelの適応

Adapting Segment Anything Model for Unseen Object Instance Segmentation

シェア:XThreadsFacebookLINEはてブBluesky

SAMを活用し、ヒートマップベースのプロンプト生成と階層的識別ネットワークで適応させることで、訓練データを10%しか使わずに未見物体のセグメンテーションで最先端性能を達成した。

著者: Rui Cao, Chuanxin Song, Biqi Yang, Jiangliu Wang, Pheng-Ann Heng, Yun-Hui Liu

分類: cs.RO, cs.CV

原文アブストラクト

Unseen Object Instance Segmentation (UOIS) is crucial for autonomous robots operating in unstructured environments. Previous approaches require full supervision on large-scale tabletop datasets for effective pretraining. In this paper, we propose UOIS-SAM, a data-efficient solution for the UOIS task that leverages SAM's high accuracy and strong generalization capabilities. UOIS-SAM integrates two key components: (i) a Heatmap-based Prompt Generator (HPG) to generate class-agnostic point prompts with precise foreground prediction, and (ii) a Hierarchical Discrimination Network (HDNet) that adapts SAM's mask decoder, mitigating issues introduced by the SAM baseline, such as background confusion and over-segmentation, especially in scenarios involving occlusion and texture-rich objects. Extensive experimental results on OCID, OSD, and additional photometrically challenging datasets including PhoCAL and HouseCat6D, demonstrate that, even using only 10% of the training samples compared to previous methods, UOIS-SAM achieves state-of-the-art performance in unseen object segmentation, highlighting its effectiveness and robustness in various tabletop scenes.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI