Lightweight Uncertainty Quantification with Simplex Semantic Segmentation for Terrain Traversability
For navigation of robots, image segmentation is an important component to determining a terrain's traversability. For safe and efficient navigation, it is key to assess the uncertainty of the predicted segments. Current uncertainty estimation methods are limited to a specific choice of model architecture, are costly in terms of training time, require large memory for inference (ensembles), or involve complex model architectures (energy-based, hyperbolic, masking). In this paper, we propose a simple, light-weight module that can be connected to any pretrained image segmentation model, regardless of its architecture, with marginal additional computation cost because it reuses the model's backbone. Our module is based on maximum separation of the segmentation classes by respective prototype vectors. This optimizes the probability that out-of-distribution segments are projected in between the prototype vectors. The uncertainty value in the classification label is obtained from the distance to the nearest prototype. We demonstrate the effectiveness of our module for terrain segmentation.
Code (0)
등록된 구현이 없습니다.
Tasks
Image SegmentationMaximum SeparationSegmentationSemantic SegmentationUncertainty QuantificationSimilar Papers 제목 키워드 기반
UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model
The introduction of the Segment Anything Model (SAM) has paved the way for numerous semantic segmentation applications. For several tasks, quantifying the uncertainty of SAM is of particular interest. However, the ambigu…
Semantic SegmentationUncertainty QuantificationA Critical Synthesis of Uncertainty Quantification and Foundation Models for Semantic Segmentation
Foundation models are increasingly breaking what seemed to be impossible not long ago by enabling unprecedented accuracy and cross-domain generalization. Yet their lack of interpretability, tendency to be overconfident, …
Semantic SegmentationDomain GeneralizationSegmentation Re-thinking Uncertainty Estimation Metrics for Semantic Segmentation
In the domain of computer vision, semantic segmentation emerges as a fundamental application within machine learning, wherein individual pixels of an image are classified into distinct semantic categories. This task tran…
Decision MakingImage SegmentationSegmentationSemantic Segmentation+1Uncertainty Quantification for Bird's Eye View Semantic Segmentation: Methods and Benchmarks
The fusion of raw features from multiple sensors on an autonomous vehicle to create a Bird's Eye View (BEV) representation is crucial for planning and control systems. There is growing interest in using deep learning mod…
Autonomous DrivingBEV SegmentationBird's-Eye View Semantic SegmentationSegmentation+2Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification
In this work, we for the first time present a method for detecting label errors in image datasets with semantic segmentation, i.e., pixel-wise class labels. Annotation acquisition for semantic segmentation datasets is ti…
BenchmarkingLabel Error DetectionSegmentationSemantic Segmentation+1