no code implementations • 15 Jan 2024 • Prarthana Bhattacharyya, Chengjie Huang, Krzysztof Czarnecki
This paper addresses motion forecasting in multi-agent environments, pivotal for ensuring safety of autonomous vehicles.
no code implementations • 8 Jan 2024 • Chengjie Huang, Vahdat Abdelzad, Sean Sedwards, Krzysztof Czarnecki
We consider the problem of cross-sensor domain adaptation in the context of LiDAR-based 3D object detection and propose Stationary Object Aggregation Pseudo-labelling (SOAP) to generate high quality pseudo-labels for stationary objects.
no code implementations • 17 May 2023 • Benjamin Thérien, Chengjie Huang, Adrian Chow, Krzysztof Czarnecki
To our knowledge, we are the first to study object re-identification from real point cloud observations.
no code implementations • 28 Sep 2022 • Chengjie Huang, Van Duong Nguyen, Vahdat Abdelzad, Christopher Gus Mannes, Luke Rowe, Benjamin Therien, Rick Salay, Krzysztof Czarnecki
Detecting OOD inputs is challenging and essential for the safe deployment of models.
1 code implementation • 28 Jun 2022 • Prarthana Bhattacharyya, Chengjie Huang, Krzysztof Czarnecki
Self-supervised learning (SSL) is an emerging technique that has been successfully employed to train convolutional neural networks (CNNs) and graph neural networks (GNNs) for more transferable, generalizable, and robust representation learning.
Ranked #59 on Motion Forecasting on Argoverse CVPR 2020
no code implementations • 1 Jun 2022 • Matthew Pitropov, Chengjie Huang, Vahdat Abdelzad, Krzysztof Czarnecki, Steven Waslander
The estimation of uncertainty in robotic vision, such as 3D object detection, is an essential component in developing safe autonomous systems aware of their own performance.
no code implementations • 30 Aug 2021 • Rick Salay, Krzysztof Czarnecki, Hiroshi Kuwajima, Hirotoshi Yasuoka, Toshihiro Nakae, Vahdat Abdelzad, Chengjie Huang, Maximilian Kahn, Van Duong Nguyen
In this paper, we propose the Integration Safety Case for Perception (ISCaP), a generic template for such a linking safety argument specifically tailored for perception components.
1 code implementation • 7 Jan 2021 • Prarthana Bhattacharyya, Chengjie Huang, Krzysztof Czarnecki
In this paper, we propose two variants of self-attention for contextual modeling in 3D object detection by augmenting convolutional features with self-attention features.
Ranked #1 on 3D Object Detection on KITTI Cyclists Hard