[4G3-OS-24d] 日常生活知識とAI

[4G3-OS-24d-02] Co-Scale Cross-Attentional Transformer for Object Rearrangement Task

〇Haruka Matsuo¹, Shintaro Ishikawa¹, Komei Sugiura¹ (1. Keio University)

Keywords:Rearrangement Target Detection, Domestic Service Robot, rearrangement task

In this paper, we propose Co-Scale Cross-Attentional Transformer for Rearrangement Target Detection, where the model generates a change mask for objects that should be rearranged.
We intorduce the Serial Encoder which consists of CoaT serial blocks and the Cross-Attentional Encoder which models the relationship between the goal and current states.
We validated our method on the new dataset, and the results demonstrated that our method outperformed a baseline method on mean IoU and F₁-score.