InstructPart: 指示に基づくタスク指向型パーツセグメンテーション
InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning
物体を構成する部品ごとに分割し、指示されたタスクに応じて適切な部品を切り出すベンチマークInstructPartを提案し、既存の視覚言語モデルでも難しいことを示した上で、データセットでの微調整により性能を倍増させるベースラインを提示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Zifu Wan, Yaqi Xie, Ce Zhang, Zhiqiu Lin, Zihan Wang, Simon Stepputtis, Deva Ramanan, Katia Sycara
分類: cs.CV, cs.CL, cs.RO
原文アブストラクト
Large multimodal foundation models, particularly in the domains of language and vision, have significantly advanced various tasks, including robotics, autonomous driving, information retrieval, and grounding. However, many of these models perceive objects as indivisible, overlooking the components that constitute them. Understanding these components and their associated affordances provides valuable insights into an object's functionality, which is fundamental for performing a wide range of tasks. In this work, we introduce a novel real-world benchmark, InstructPart, comprising hand-labeled part segmentation annotations and task-oriented instructions to evaluate the performance of current models in understanding and executing part-level tasks within everyday contexts. Through our experiments, we demonstrate that task-oriented part segmentation remains a challenging problem, even for state-of-the-art Vision-Language Models (VLMs). In addition to our benchmark, we introduce a simple baseline that achieves a twofold performance improvement through fine-tuning with our dataset. With our dataset and benchmark, we aim to facilitate research on task-oriented part segmentation and enhance the applicability of VLMs across various domains, including robotics, virtual reality, information retrieval, and other related fields. Project website: https://zifuwan.github.io/InstructPart/.
