他タスクの視点で自らの失敗を検知するマルチタスク注意機構
See Yourself in Others: Attending Multiple Tasks for Own Failure Detection
セグメンテーションや深度推定など複数の視覚タスク間の相関を注意ネットワークで活用し、各タスクの予測失敗を検出する手法を提案した論文。
著者: Boyang Sun, Jiaxu Xing, Hermann Blum, Roland Siegwart, Cesar Cadena
分類: cs.CV, cs.RO
原文アブストラクト
Autonomous robots deal with unexpected scenarios in real environments. Given input images, various visual perception tasks can be performed, e.g., semantic segmentation, depth estimation and normal estimation. These different tasks provide rich information for the whole robotic perception system. All tasks have their own characteristics while sharing some latent correlations. However, some of the task predictions may suffer from the unreliability dealing with complex scenes and anomalies. We propose an attention-based failure detection approach by exploiting the correlations among multiple tasks. The proposed framework infers task failures by evaluating the individual prediction, across multiple visual perception tasks for different regions in an image. The formulation of the evaluations is based on an attention network supervised by multi-task uncertainty estimation and their corresponding prediction errors. Our proposed framework generates more accurate estimations of the prediction error for the different task's predictions.
