Search Results for author:
Found 8 papers, 5 papers with code
What Matters in Range View 3D Object Detection
Combining the above findings, we establish a new state-of-the-art model for range-view 3D object detection -- improving AP by 2. 2% on the Waymo Open dataset while maintaining a runtime of 10 Hz.
An Empirical Analysis of Range for 3D Object Detection
LiDAR-based 3D detection plays a vital role in autonomous navigation.
Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting
Models are tasked with the prediction of future motion for "scored actors" in each scenario and are provided with track histories that capture object location, heading, velocity, and category.
NukeLM: Pre-Trained and Fine-Tuned Language Models for the Nuclear and Energy Domains
The BERT architecture has shown even better performance on domain-specific tasks when the model is pre-trained using domain-relevant texts.
Learning phylogenetic trees as hyperbolic point configurations
The objective function, which is shown to mimic the log-likelihood on tree space, is a differentiable function on a Riemannian manifold.
3D for Free: Crossmodal Transfer Learning using HD Maps
In this work, we address the long-tail problem by leveraging both the large class-taxonomies of modern 2D datasets and the robustness of state-of-the-art 2D detection methods.
Predictive Inequity in Object Detection
In this work, we investigate whether state-of-the-art object detection systems have equitable predictive performance on pedestrians with different skin tones.
Gradient descent in hyperbolic space
Gradient descent generalises naturally to Riemannian manifolds, and to hyperbolic $n$-space, in particular.
Optimization and Control I.2.0
