Search Results for author:
Found 6 papers, 4 papers with code
Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions
Deep neural networks for scene perception in automated vehicles achieve excellent results for the domains they were trained on.
Effects of Architectures on Continual Semantic Segmentation
Specifically, we compare the well-researched CNNs to recently proposed Transformers and Hybrid architectures, as well as the impact of the choice of novel normalization layers and different decoder heads.
Improving Replay-Based Continual Semantic Segmentation with Smart Data Selection
Continual learning for Semantic Segmentation (CSS) is a rapidly emerging field, in which the capabilities of the segmentation model are incrementally improved by learning new classes or new domains.
Continual Learning for Class- and Domain-Incremental Semantic Segmentation
Therefore, the goal of our work is to evaluate and adapt established solutions for continual object recognition to the task of semantic segmentation and to provide baseline methods and evaluation protocols for the task of continual semantic segmentation.
Class-Incremental Semantic Segmentation
Continual Semantic Segmentation
+6
Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation
Therefore, in a set of experiments and representational analyses, we demonstrate that the semantic shift of the background class and a bias towards new classes are the major causes of forgetting in CiSS.
Class-Incremental Semantic Segmentation
Incremental Learning
+2
Human Pose Estimation for Real-World Crowded Scenarios
In order to overcome the transfer gap of JTA originating from a low pose variety and less dense crowds, an extension dataset is created to ease the use for real-world applications.
Ranked #14 on
Multi-Person Pose Estimation
on CrowdPose
