WildDash - Creating Hazard-Aware Benchmarks

Zendel, Oliver; Honauer, Katrin; Murschitz, Markus; Steininger, Daniel; Domínguez, Gustavo Fernández

doi:10.1007/978-3-030-01231-1_25

Cited by 148 publications

(142 citation statements)

References 13 publications

Supporting

Mentioning

140

Contrasting

Unclassified

Order By: Relevance

“…regions with indiscernible semantic content. Invalid regions are closely related to the concept of negative test cases which was considered in [40]. However, invalid regions constitute intra-image entities and can co-exist with valid regions in the same image, whereas a negative test case refers to an entire image that should be treated as invalid.…”

Section: Uncertainty-aware Evaluationmentioning

confidence: 99%

“…However, invalid regions constitute intra-image entities and can co-exist with valid regions in the same image, whereas a negative test case refers to an entire image that should be treated as invalid. We build upon the evaluation of [40] for negative test cases and generalize it to be applied uniformly to all images in the evaluation set, whether they contain invalid regions or not. Our annotation and evaluation framework includes invalid regions in the set of evaluated pixels, but treats them differently from valid regions to account for the high uncertainty of their content.…”

Section: Uncertainty-aware Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

Sakaridis

Dai

Gool

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

208

122

View full text Add to dashboard Cite

show abstract

Section: Uncertainty-aware Evaluationmentioning

confidence: 99%

Section: Uncertainty-aware Evaluationmentioning

confidence: 99%

Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

Sakaridis

Dai

Gool

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

208

122

View full text Add to dashboard Cite

show abstract

“…The two-head model performs better in most classic evaluation categories as well as in the negative category, however it has a lower meta average score. Table 6 explores influence of WildDash hazards [47] on the performance of the two models. The C-way multi-class model has a lower performance drop in most hazard categories.…”

Section: Comparing the Two-head And C-way Multi-class Modelsmentioning

confidence: 99%

“…The described deficiencies emphasize the need for a more robust approach to dataset design. First, an ideal dataset should identify and target a set of explicit hazards for the particular domain [47]. Second (and more important), an ideal dataset should endorse open-set recognition paradigm [39] in order to promote detection of unforeseen hazards.…”

Section: Introductionmentioning

confidence: 99%

Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift

Bevandić

Krešo

Oršić

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Recent success on realistic road driving datasets has increased interest in exploring robust performance in real-world applications. One of the major unsolved problems is to identify image content which can not be reliably recognized with a given inference engine. We therefore study approaches to recover a dense outlier map alongside the primary task with a single forward pass, by relying on shared convolutional features. We consider semantic segmentation as the primary task and perform extensive validation on WildDash val (inliers), LSUN val (outliers), and pasted objects from Pascal VOC 2007 (outliers). We achieve the best validation performance by training to discriminate inliers from pasted ImageNet-1k content, even though ImageNet-1k contains many roaddriving pixels, and, at least nominally, fails to account for the full diversity of the visual world. The proposed two-head model performs comparably to the C-way multi-class model trained to predict uniform distribution in outliers, while outperforming several other validated approaches. We evaluate our best two models on the WildDash test dataset and set a new state of the art on the WildDash benchmark.

show abstract

“…If one of the assignments can be predicted from the other, then all information conveyed by X is shared with Y and NMI(X; Y ) = 1. In addition to the Cityscapes dataset, we also compare the cluster assignments with the same 19 classes on the Wild-Dash dataset [96], which is designed to evaluate the robustness of segmentation methods under a wide range of conditions. Tab.…”

Section: Semantic Information In Clustersmentioning

confidence: 99%

Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization

Larsson

Stenborg

Toft

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Long-term visual localization is the problem of estimating the camera pose of a given query image in a scene whose appearance changes over time. It is an important problem in practice, for example, encountered in autonomous driving. In order to gain robustness to such changes, long-term localization approaches often use segmantic segmentations as an invariant scene representation, as the semantic meaning of each scene part should not be affected by seasonal and other changes. However, these representations are typically not very discriminative due to the limited number of available classes. In this paper, we propose a new neural network, the Fine-Grained Segmentation Network (FGSN), that can be used to provide image segmentations with a larger number of labels and can be trained in a self-supervised fashion. In addition, we show how FGSNs can be trained to output consistent labels across seasonal changes. We demonstrate through extensive experiments that integrating the fine-grained segmentations produced by our FGSNs into existing localization algorithms leads to substantial improvements in localization performance.

show abstract

WildDash - Creating Hazard-Aware Benchmarks

Cited by 148 publications

References 13 publications

Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift

Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization

Contact Info

Product

Resources

About