4 papers · 1 filter
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…
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…