Detection of False Positive and False Negative Samples in Semantic Segmentation

In recent years, deep learning methods have outperformed other methods in image recognition. This has fostered imagination of potential application of deep learning technology including safety relevant applications like the interpretation of medical images or autonomous driving. The passage from assistance of a human decision maker to ever more automated systems however increases the need to properly handle the failure modes of deep learning modules. In this contribution, we review a set of techniques for the self-monitoring of machine-learning algorithms based on uncertainty quantification. In particular, we apply this to the task of semantic segmentation, where the machine learning algorithm decomposes an image according to semantic categories. We discuss false positive and false negative error modes at instance-level and review techniques for the detection of such errors that have been recently proposed by the authors. We also give an outlook on future research directions.

[1]  Hanno Gottschalk,et al.  Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilities , 2018, 2020 International Joint Conference on Neural Networks (IJCNN).

[2]  Hanno Gottschalk,et al.  Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks , 2019, 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI).

[3]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[4]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[5]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[7]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Kevin Gimpel,et al.  A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks , 2016, ICLR.

[9]  Tarek Khadir,et al.  Deep Convolutional Neural Networks Using U-Net for Automatic Brain Tumor Segmentation in Multimodal MRI Volumes , 2018, BrainLes@MICCAI.

[10]  Graham W. Taylor,et al.  Leveraging Uncertainty Estimates for Predicting Segmentation Quality , 2018, ArXiv.

[11]  Hanno Gottschalk,et al.  The Ethical Dilemma When (Not) Setting up Cost-Based Decision Rules in Semantic Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[12]  R. Srikant,et al.  Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks , 2017, ICLR.

[13]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[15]  Hanno Gottschalk,et al.  Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation , 2019, ArXiv.

[16]  Thomas Schamm,et al.  Autonomous driving , 2015, it Inf. Technol..

[17]  Itf,et al.  Automated and Autonomous Driving: Regulation under Uncertainty , 2015 .

[18]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[19]  Luís Torgo,et al.  SMOTE for Regression , 2013, EPIA.

[20]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[22]  Yu Liu,et al.  A review of semantic segmentation using deep neural networks , 2017, International Journal of Multimedia Information Retrieval.

[23]  Harris Drucker,et al.  Comparison of learning algorithms for handwritten digit recognition , 1995 .

[24]  Matthias Hein,et al.  Towards neural networks that provably know when they don't know , 2020, ICLR.

[25]  G. Pflug,et al.  Modeling, Measuring and Managing Risk , 2008 .

[26]  Willem Waegeman,et al.  Aleatoric and Epistemic Uncertainty in Machine Learning: A Tutorial Introduction , 2019, ArXiv.

[27]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[28]  Matthias Rottmann,et al.  Uncertainty Measures and Prediction Quality Rating for the Semantic Segmentation of Nested Multi Resolution Street Scene Images , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[29]  Hanno Gottschalk,et al.  Classification Uncertainty of Deep Neural Networks Based on Gradient Information , 2018, ANNPR.

[30]  Chao Huang,et al.  QualityNet: Segmentation quality evaluation with deep convolutional networks , 2016, 2016 Visual Communications and Image Processing (VCIP).

[31]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).