# See Yourself in Others: Attending Multiple Tasks for Own Failure Detection Source: [See Yourself in Others: Attending Multiple Tasks for Own Failure Detection]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:59:56.170Z Authors: Boyang Sun, Jiaxu Xing, Hermann Blum, Roland Siegwart, Cesar Cadena Published: 2021-10-06T07:42:57.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()