Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shift

Abstract

While recent computer vision algorithms achieve impressive performance on many benchmarks, they lack robustness - presented with an image from a different distribution, (e.g. weather or lighting conditions not considered during training), they may produce an erroneous prediction. Therefore, it is desired that such a model will be able to reliably predict its confidence measure. In this work, uncertainty estimation for the task of semantic segmentation is evaluated under a varying level of domain shift: in a cross-dataset setting and when adapting a model trained on data from the simulation. It was shown that simple color transformations already provide a strong baseline, comparable to using more sophisticated style-transfer data augmentation. Further, by constructing an ensemble consisting of models using different backbones and/or augmentation methods, it was possible to improve significantly model performance in terms of overall accuracy and uncertainty estimation under the domain shift setting. The Expected Calibration Error (ECE) on challenging GTA to Cityscapes adaptation was reduced from 4.05 to the competitive value of 1.1. Further, an ensemble of models was utilized in the self-training setting to improve the pseudo-labels generation, which resulted in a significant gain in the final model accuracy, compared to the standard fine-tuning (without ensemble).

arXiv commentInternational Joint Conference on Neural Networks 2021, https://ieeexplore.ieee.org/document/9533330

References in corpus (13)

• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• On Calibration of Modern Neural Networks
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
• Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation
• What is being transferred in transfer learning?
• Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
• The Origins and Prevalence of Texture Bias in Convolutional Neural Networks
• Benchmarking the Robustness of Semantic Segmentation Models
• BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning
• Keep it Simple: Image Statistics Matching for Domain Adaptation
• EDF: Ensemble, Distill, and Fuse for Easy Video Labeling
• Robustness in Compressed Neural Networks for Object Detection