Pixel wise Anomaly Detection in Complex Driving Scenes
CVPR Talk for our paper "Pixel-Wise Anomaly Detection in Complex Driving Scenes"
Paper Link: https://arxiv.org/abs/2103.05445
Code Link: https://github.com/giandbt/synboost
Abstract:
The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as autonomous driving. Recent approaches have focused on either leveraging segmentation uncertainty to identify anomalous areas or re-synthesizing the image from the semantic label map to find dissimilarities with the input image. In this work, we demonstrate that these two methodologies contain complementary information and can be combined to produce robust predictions for anomaly segmentation. We present a pixel-wise anomaly detection framework that uses uncertainty maps to improve over existing re-synthesis methods in finding dissimilarities between the input and generated images. Our approach works as a general framework around already trained segmentation networks, which ensures anomaly detection without compromising segmentation accuracy, while significantly outperforming all similar methods. Top-2 performance across a range of different anomaly datasets shows the robustness of our approach to handling different anomaly instances.
Видео Pixel wise Anomaly Detection in Complex Driving Scenes канала aslteam
Paper Link: https://arxiv.org/abs/2103.05445
Code Link: https://github.com/giandbt/synboost
Abstract:
The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as autonomous driving. Recent approaches have focused on either leveraging segmentation uncertainty to identify anomalous areas or re-synthesizing the image from the semantic label map to find dissimilarities with the input image. In this work, we demonstrate that these two methodologies contain complementary information and can be combined to produce robust predictions for anomaly segmentation. We present a pixel-wise anomaly detection framework that uses uncertainty maps to improve over existing re-synthesis methods in finding dissimilarities between the input and generated images. Our approach works as a general framework around already trained segmentation networks, which ensures anomaly detection without compromising segmentation accuracy, while significantly outperforming all similar methods. Top-2 performance across a range of different anomaly datasets shows the robustness of our approach to handling different anomaly instances.
Видео Pixel wise Anomaly Detection in Complex Driving Scenes канала aslteam
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Design and Control of a Micro Overactuated Aerial Robot with an Origami Delta ManipulatorRegistration Study Case: Object ModelingAutonomous Christmas Lab 2014 TeaserArtistic pattern formation with multiple robotsUnder the Sand: A UAV with Ground Penetrating Synthetic Aperture RadarAutonomous Christmas Lab 2022Collaborative Transportation (Complete Version)Dynamic Walking 2014Image and Animation Display with Multiple Mobile RobotsInnovationsprojekt 2011Embedded Visual-Inertial OdometryThis is Ascento ProDynamic Object Aware LiDAR SLAM based on Automatic Generation of Training DatasFly – Swarm of Micro Flying RobotsDesign and optimal control of a tiltrotor micro aerial vehicle for efficient omnidirectional flightStarlETH at ICRA 2013Football field reconstruction from monocular imagesSampling-based Motion Planning for Active Multirotor System IdentificationInnovationsprojekt 2012Avalon Sailing Autonomously