再現可能なマルチモーダル・アフォーダンス予測
Reproducible Multimodal Affordance Prediction
アフォーダンス予測の評価・比較を困難にする問題を解決するため、実験プロトコルやデータセットなどを詳細に記録する「アフォーダンスシート」を提案し、再現可能なベンチマークと信頼性の高い評価を可能にした。
著者: Tommaso Apicella, Alessio Xompero, Andrea Cavallaro
分類: cs.CV, cs.RO
原文アブストラクト
Affordance prediction is the identification of potential actions an agent can perform on a target object from multimodal inputs. Affordance prediction methods are difficult to evaluate and compare due to heterogeneous problem formulations, inconsistent dataset annotations, incomplete reporting of experimental protocols, and limited information about deployment conditions. These limitations challenge fair benchmarking and performance comparison. To promote transparency, we propose the Affordance Sheet, a documentation detailing task formulation with its input modalities, model architectures and training information, datasets, and experimental protocols. Affordance Sheets enable reproducible benchmarking and reliable evaluation of affordance models for real-world scenarios, including generalisation to novel conditions and human safety.