Indeed, the subtasks are executed sequentially, leading to increased processing latency and a compounding of errors through the pipeline.
We evaluate our approach on several complex systems and tasks, and experimentally analyze the advantages over model-free and model-based methods in terms of performance and sample efficiency.
Deep graph neural networks (GNNs) have achieved excellent results on various tasks on increasingly large graph datasets with millions of nodes and edges.
Ranked #1 on Node Property Prediction on ogbn-proteins
We develop a software stack that allows smartphones to use this body for mobile operation and demonstrate that the system is sufficiently powerful to support advanced robotics workloads such as person following and real-time autonomous navigation in unstructured environments.
In this paper, we propose to learn a sensorimotor policy that enables an autonomous quadrotor to fly extreme acrobatic maneuvers with only onboard sensing and computation.
Architecture design has become a crucial component of successful deep learning.
Ranked #3 on Node Classification on PPI
This work transfers concepts such as residual/dense connections and dilated convolutions from CNNs to GCNs in order to successfully train very deep GCNs.
Ranked #4 on Node Classification on PPI
A common approach is to learn an end-to-end policy that directly predicts controls from raw images by imitating an expert.
Finally, we use these new concepts to build a very deep 56-layer GCN, and show how it significantly boosts performance (+3. 7% mIoU over state-of-the-art) in the task of point cloud semantic segmentation.
In contrast, we present a general framework for adversarial attacks on trained agents, which covers semantic perturbations to the environment of the agent performing the task as well as pixel-level attacks.
Simulation can help end-to-end driving systems by providing a cheap, safe, and diverse training environment.
In this work, we present TrackingNet, the first large-scale dataset and benchmark for object tracking in the wild.
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, driving policies trained via imitation learning cannot be controlled at test time.
We present a photo-realistic training and evaluation simulator (Sim4CV) with extensive applications across various fields of computer vision.
Automating the navigation of unmanned aerial vehicles (UAVs) in diverse scenarios has gained much attention in recent years.