Anomaly-Aware Semantic Segmentation by Leveraging Synthetic-Unknown Data

11/29/2021
by   Guan-Rong Lu, et al.
0

Anomaly awareness is an essential capability for safety-critical applications such as autonomous driving. While recent progress of robotics and computer vision has enabled anomaly detection for image classification, anomaly detection on semantic segmentation is less explored. Conventional anomaly-aware systems assuming other existing classes as out-of-distribution (pseudo-unknown) classes for training a model will result in two drawbacks. (1) Unknown classes, which applications need to cope with, might not actually exist during training time. (2) Model performance would strongly rely on the class selection. Observing this, we propose a novel Synthetic-Unknown Data Generation, intending to tackle the anomaly-aware semantic segmentation task. We design a new Masked Gradient Update (MGU) module to generate auxiliary data along the boundary of in-distribution data points. In addition, we modify the traditional cross-entropy loss to emphasize the border data points. We reach the state-of-the-art performance on two anomaly segmentation datasets. Ablation studies also demonstrate the effectiveness of proposed modules.

READ FULL TEXT

page 2

page 6

research
08/04/2023

Synthetic outlier generation for anomaly detection in autonomous driving

Anomaly detection, or outlier detection, is a crucial task in various do...
research
08/19/2023

Anomaly-Aware Semantic Segmentation via Style-Aligned OoD Augmentation

Within the context of autonomous driving, encountering unknown objects b...
research
03/18/2020

Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation

The ability to detect failures and anomalies are fundamental requirement...
research
07/13/2022

Experiments on Anomaly Detection in Autonomous Driving by Forward-Backward Style Transfers

Great progress has been achieved in the community of autonomous driving ...
research
03/19/2021

Video Class Agnostic Segmentation Benchmark for Autonomous Driving

Semantic segmentation approaches are typically trained on large-scale da...
research
08/13/2019

Detecting semantic anomalies

We critically appraise the recent interest in out-of-distribution (OOD) ...
research
07/19/2023

U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentation

Deep neural networks have shown exceptional performance in various tasks...

Please sign up or login with your details

Forgot password? Click here to reset