5 citations · 8 across the 7 of their papers we have counts for
7 papers
Mask What Matters: Saliency-Guided Video Self-Supervised Learning for Autonomous Driving
Christopher Lang, Alexander Braun, Abhinav Valada
Video self-supervised learning through masked spatiotemporal prediction has emerged as a promising paradigm for learning feature representations from unlabeled data. However, exist…
A Point-Based Approach to Efficient LiDAR Multi-Task Perception
Christopher Lang, Alexander Braun, Lars Schillingmann +1
Multi-task networks can potentially improve performance and computational efficiency compared to single-task networks, facilitating online deployment. However, current multi-task a…
Self-Supervised Multi-Object Tracking For Autonomous Driving From Consistency Across Timescales
Christopher Lang, Alexander Braun, Lars Schillingmann +1
Self-supervised multi-object trackers have tremendous potential as they enable learning from raw domain-specific data. However, their re-identification accuracy still falls short c…
Self-Supervised Representation Learning from Temporal Ordering of Automated Driving Sequences
Christopher Lang, Alexander Braun, Lars Schillingmann +2
Self-supervised feature learning enables perception systems to benefit from the vast raw data recorded by vehicle fleets worldwide. While video-level self-supervised learning appro…
Change Detection for Local Explainability in Evolving Data Streams
Johannes Haug, Alexander Braun, Stefan Zürn +1
As complex machine learning models are increasingly used in sensitive applications like banking, trading or credit scoring, there is a growing demand for reliable explanation mecha…
On Hyperbolic Embeddings in 2D Object Detection
Christopher Lang, Alexander Braun, Abhinav Valada
Object detection, for the most part, has been formulated in the euclidean space, where euclidean or spherical geodesic distances measure the similarity of an image region to an obj…
Contrastive Object Detection Using Knowledge Graph Embeddings
Christopher Lang, Alexander Braun, Abhinav Valada
Object recognition for the most part has been approached as a one-hot problem that treats classes to be discrete and unrelated. Each image region has to be assigned to one member o…