Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentation

05/14/2020
by   Philipp Oberdiek, et al.
48

When deploying deep learning technology in self-driving cars, deep neural networks are constantly exposed to domain shifts. These include, e.g., changes in weather conditions, time of day, and long-term temporal shift. In this work we utilize a deep neural network trained on the Cityscapes dataset containing urban street scenes and infer images from a different dataset, the A2D2 dataset, containing also countryside and highway images. We present a novel pipeline for semantic segmenation that detects out-of-distribution (OOD) segments by means of the deep neural network's prediction and performs image retrieval after feature extraction and dimensionality reduction on image patches. In our experiments we demonstrate that the deployed OOD approach is suitable for detecting out-of-distribution concepts. Furthermore, we evaluate the image patch retrieval qualitatively as well as quantitatively by means of the semi-compatible A2D2 ground truth and obtain mAP values of up to 52.2

READ FULL TEXT

page 1

page 5

page 7

page 8

research
05/25/2020

Visual Localization Using Semantic Segmentation and Depth Prediction

In this paper, we propose a monocular visual localization pipeline lever...
research
06/14/2018

Semantic Image Retrieval by Uniting Deep Neural Networks and Cognitive Architectures

Image and video retrieval by their semantic content has been an importan...
research
12/23/2020

Pit30M: A Benchmark for Global Localization in the Age of Self-Driving Cars

We are interested in understanding whether retrieval-based localization ...
research
12/30/2018

Impact of Ground Truth Annotation Quality on Performance of Semantic Image Segmentation of Traffic Conditions

Preparation of high-quality datasets for the urban scene understanding i...
research
03/02/2022

MUAD: Multiple Uncertainties for Autonomous Driving benchmark for multiple uncertainty types and tasks

Predictive uncertainty estimation is essential for deploying Deep Neural...
research
06/05/2018

Performance Evaluation of Deep Learning Networks for Semantic Segmentation of Traffic Stereo-Pair Images

Semantic image segmentation is one the most demanding task, especially f...
research
04/18/2022

Multiple-environment Self-adaptive Network for Aerial-view Geo-localization

Aerial-view geo-localization tends to determine an unknown position thro...

Please sign up or login with your details

Forgot password? Click here to reset