351 citations · 1.1k across the 12 of their papers we have counts for
15 papers
GIM: Learning Generalizable Image Matcher From Internet Videos
Xuelun Shen, Zhipeng Cai, Wei Yin +5
Image matching is a fundamental computer vision problem. While learning-based methods achieve state-of-the-art performance on existing benchmarks, they generalize poorly to in-the-…
Label Delay in Online Continual Learning
Botos Csaba, Wenxuan Zhang, Matthias Müller +4
Online continual learning, the process of training models on streaming data, has gained increasing attention in recent years. However, a critical aspect often overlooked is the lab…
Learning High-Speed Flight in the Wild
Antonio Loquercio, Elia Kaufmann, René Ranftl +3
Quadrotors are agile. Unlike most other machines, they can traverse extremely complex environments at high speeds. To date, only expert human pilots have been able to fully exploit…
Training Graph Neural Networks with 1000 Layers
Guohao Li, Matthias Müller, Bernard Ghanem +1
Deep graph neural networks (GNNs) have achieved excellent results on various tasks on increasingly large graph datasets with millions of nodes and edges. However, memory complexity…
OpenBot: Turning Smartphones into Robots
Matthias Müller, Vladlen Koltun
Current robots are either expensive or make significant compromises on sensory richness, computational power, and communication capabilities. We propose to leverage smartphones to…
Deep Drone Acrobatics
Elia Kaufmann, Antonio Loquercio, René Ranftl +3
Performing acrobatic maneuvers with quadrotors is extremely challenging. Acrobatic flight requires high thrust and extreme angular accelerations that push the platform to its physi…
SGAS: Sequential Greedy Architecture Search
Guohao Li, Guocheng Qian, Itzel C. Delgadillo +3
Architecture design has become a crucial component of successful deep learning. Recent progress in automatic neural architecture search (NAS) shows a lot of promise. However, disco…
DeepGCNs: Making GCNs Go as Deep as CNNs
Guohao Li, Matthias Müller, Guocheng Qian +4
Convolutional Neural Networks (CNNs) have been very successful at solving a variety of computer vision tasks such as object classification and detection, semantic segmentation, act…
Learning a Controller Fusion Network by Online Trajectory Filtering for Vision-based UAV Racing
Matthias Müller, Guohao Li, Vincent Casser +3
Autonomous UAV racing has recently emerged as an interesting research problem. The dream is to beat humans in this new fast-paced sport. A common approach is to learn an end-to-end…
DeepGCNs: Can GCNs Go as Deep as CNNs?
Guohao Li, Matthias Müller, Ali Thabet +1
Convolutional Neural Networks (CNNs) achieve impressive performance in a wide variety of fields. Their success benefited from a massive boost when very deep CNN models were able to…
SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications
Abdullah Hamdi, Matthias Müller, Bernard Ghanem
One major factor impeding more widespread adoption of deep neural networks (DNNs) is their lack of robustness, which is essential for safety-critical applications such as autonomou…
Driving Policy Transfer via Modularity and Abstraction
Matthias Müller, Alexey Dosovitskiy, Bernard Ghanem +1
End-to-end approaches to autonomous driving have high sample complexity and are difficult to scale to realistic urban driving. Simulation can help end-to-end driving systems by pro…
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
Matthias Müller, Adel Bibi, Silvio Giancola +2
Despite the numerous developments in object tracking, further development of current tracking algorithms is limited by small and mostly saturated datasets. As a matter of fact, dat…
OIL: Observational Imitation Learning
Guohao Li, Matthias Müller, Vincent Casser +3
Recent work has explored the problem of autonomous navigation by imitating a teacher and learning an end-to-end policy, which directly predicts controls from raw images. However, t…
Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications
Matthias Müller, Vincent Casser, Jean Lahoud +2
We present a photo-realistic training and evaluation simulator (Sim4CV) with extensive applications across various fields of computer vision. Built on top of the Unreal Engine, the…