Controlled False Negative Reduction of Minority Classes in Semantic Segmentation

Chan, Robin; Rottmann, Matthias; Hüger, Fabian; Schlicht, Peter; Gottschalk, Hanno

doi:10.1109/ijcnn48605.2020.9207104

Cited by 17 publications

(19 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the latter case, this would yield false positive anomaly instance predictions, which, however, can be identified and discarded afterwards by meta classification. The concept of trading false-positive detection for anomaly detection performance is motivated by [Cha+20]. Moreover, meta classifiers are expected to considerably benefit from entropy maximization, since in the original work [Rot+20] the entropy as metric has already been observed to be well correlated to the segment-wise IoU.…”

Section: Combining Entropy Maximization and Meta Classificationmentioning

confidence: 99%

Detecting and Learning the Unknown in Semantic Segmentation

Chan¹,

Svenja²,

Rottmann³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Semantic segmentation is a crucial component for perception in automated driving. Deep neural networks (DNNs) are commonly used for this task and they are usually trained on a closed set of object classes appearing in a closed operational domain. However, this is in contrast to the open world assumption in automated driving that DNNs are deployed to. Therefore, DNNs necessarily face data that they have never encountered previously, also known as anomalies, which are extremely safety-critical to properly cope with.In this work, we first give an overview about anomalies from an information-theoretic perspective. Next, we review research in detecting semantically unknown objects in semantic segmentation. We demonstrate that training for high entropy responses on anomalous objects outperforms other recent methods, which is in line with our theoretical findings. Moreover, we examine a method to assess the occurrence frequency of anomalies in order to select anomaly types to include into a model's set of semantic categories. We demonstrate that these anomalies can then be learned in an unsupervised fashion, which is particularly suitable in online applications based on deep learning.

show abstract

Section: Combining Entropy Maximization and Meta Classificationmentioning

confidence: 99%

Detecting and Learning the Unknown in Semantic Segmentation

Chan¹,

Svenja²,

Rottmann³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The similar approach in [16] uses an importance-aware loss function to improve the networks' reliability. In [17], the differences between the Maximum Likelihood and the Bayes decision rule are considered to reduce false negatives of minority classes by introducing class priors which assign larger weight to underrepresented classes. The following methods address false negative reduction for the object detection task.…”

Section: Related Workmentioning

confidence: 99%

False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates

Maag¹

2021

Preprint

View full text Add to dashboard Cite

Instance segmentation of images is an important tool for automated scene understanding. Neural networks are usually trained to optimize their overall performance in terms of accuracy. Meanwhile, in applications such as automated driving, an overlooked pedestrian seems more harmful than a falsely detected one. In this work, we present a false negative detection method for image sequences based on inconsistencies in time series of tracked instances given the availability of image sequences in online applications. As the number of instances can be greatly increased by this algorithm, we apply a false positive pruning using uncertainty estimates aggregated over instances. To this end, instance-wise metrics are constructed which characterize uncertainty and geometry of a given instance or are predicated on depth estimation. The proposed method serves as a post-processing step applicable to any neural network that can also be trained on single frames only. In our tests, we obtain an improved trade-off between false negative and false positive instances by our fused detection approach in comparison to the use of an ordinary score value provided by the instance segmentation network during inference.

show abstract

“…First, the blood vessel in the 3D modality is represented with small cross-sectional areas of less than 1% of an image. This severe lack of information about the blood vessel causes a class imbalance and causes the training stage to be dominated by the non-vessel area, resulting in a tendency to produce false negative pixels [23]. Augmenting information about the blood vessel with adjacent slices would be helpful to alleviate this problem.…”

Section: Introductionmentioning

confidence: 99%

Spider U-Net: Incorporating Inter-Slice Connectivity Using LSTM for 3D Blood Vessel Segmentation

et al. 2021

View full text Add to dashboard Cite

Blood vessel segmentation (BVS) of 3D medical imaging such as computed tomography and magnetic resonance angiography (MRA) is an essential task in the clinical field. Automation of 3D BVS using deep supervised learning is being researched, and U-Net-based approaches, which are considered as standard for medical image segmentation, are proposed a lot. However, the inherent characteristics of blood vessels, e.g., they are complex and narrow, as well as the resolution and sensitivity of the imaging modalities increases the difficulty of 3D BVS. We propose a novel U-Net-based model named Spider U-Net for 3D BVS that considers the connectivity of the blood vessels between the axial slices. To achieve this, long short-term memory (LSTM), which can capture the context of the consecutive data, is inserted into the baseline model. We also propose a data feeding strategy that augments data and makes Spider U-Net stable. Spider U-Net outperformed 2D U-Net, 3D U-Net, and the fully convolutional network-recurrent neural network (FCN-RNN) in dice coefficient score (DSC) by 0.048, 0.077, and 0.041, respectively, for our in-house brain MRA dataset and also achieved the highest DSC for two public datasets. The results imply that considering inter-slice connectivity with LSTM improves model performance in the 3D BVS task.

show abstract

Controlled False Negative Reduction of Minority Classes in Semantic Segmentation

Cited by 17 publications

References 28 publications

Detecting and Learning the Unknown in Semantic Segmentation

Detecting and Learning the Unknown in Semantic Segmentation

False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates

Spider U-Net: Incorporating Inter-Slice Connectivity Using LSTM for 3D Blood Vessel Segmentation

Contact Info

Product

Resources

About