DialMAT: 対話可能なTransformerとモーメントベース敵対的学習
DialMAT: Dialogue-Enabled Transformer with Moment-Based Adversarial Training
対話を通じて指示を確認できる具現化エージェント向けに、言語・画像・行動の潜在空間に敵対的摂動を加える学習法とクロスモーダル特徴抽出を組み合わせたDialMATを提案し、DialFREDタスクで最高性能を達成した。
著者: Kanta Kaneda, Ryosuke Korekata, Yuiga Wada, Shunya Nagashima, Motonari Kambara, Yui Iioka, Haruka Matsuo, Yuto Imai, Takayuki Nishimura, Komei Sugiura
分類: cs.CV, cs.CL, cs.RO
原文アブストラクト
This paper focuses on the DialFRED task, which is the task of embodied instruction following in a setting where an agent can actively ask questions about the task. To address this task, we propose DialMAT. DialMAT introduces Moment-based Adversarial Training, which incorporates adversarial perturbations into the latent space of language, image, and action. Additionally, it introduces a crossmodal parallel feature extraction mechanism that applies foundation models to both language and image. We evaluated our model using a dataset constructed from the DialFRED dataset and demonstrated superior performance compared to the baseline method in terms of success rate and path weighted success rate. The model secured the top position in the DialFRED Challenge, which took place at the CVPR 2023 Embodied AI workshop.
