This is not what I imagined: Error Detection for Semantic Segmentation through Visual Dissimilarity

09/02/2019
by   David Haldimann, et al.
20

There has been a remarkable progress in the accuracy of semantic segmentation due to the capabilities of deep learning. Unfortunately, these methods are not able to generalize much further than the distribution of their training data and fail to handle out-of-distribution classes appropriately. This limits the applicability to autonomous or safety critical systems. We propose a novel method leveraging generative models to detect wrongly segmented or out-of-distribution instances. Conditioned on the predicted semantic segmentation, an RGB image is generated. We then learn a dissimilarity metric that compares the generated image with the original input and detects inconsistencies introduced by the semantic segmentation. We present test cases for outlier and misclassification detection and evaluate our method qualitatively and quantitatively on multiple datasets.

READ FULL TEXT

page 2

page 4

page 5

page 6

page 9

research
08/10/2021

Deep Metric Learning for Open World Semantic Segmentation

Classical close-set semantic segmentation networks have limited ability ...
research
11/07/2019

Efficacy of Pixel-Level OOD Detection for Semantic Segmentation

The detection of out of distribution samples for image classification ha...
research
04/05/2019

The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation

Deep learning has enabled impressive progress in the accuracy of semanti...
research
11/11/2022

A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation

Safety-critical applications like autonomous driving use Deep Neural Net...
research
08/03/2021

Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation

In this paper, we tackle the detection of out-of-distribution (OOD) obje...
research
09/02/2020

On the Structures of Representation for the Robustness of Semantic Segmentation to Input Corruption

Semantic segmentation is a scene understanding task at the heart of safe...
research
12/02/2021

"Just Drive": Colour Bias Mitigation for Semantic Segmentation in the Context of Urban Driving

Biases can filter into AI technology without our knowledge. Oftentimes, ...

Please sign up or login with your details

Forgot password? Click here to reset