1 code implementation • 19 Apr 2024 • Mostafa ElAraby, Ali Harakeh, Liam Paull
Besides the common problem of classical catastrophic forgetting in the continual learning setting, CSS suffers from the inherent ambiguity of the background, a phenomenon we refer to as the "background shift'', since pixels labeled as background could correspond to future classes (forward background shift) or previous classes (backward background shift).
no code implementations • CVPR 2023 • Anas Mahmoud, Jordan S. K. Hu, Tianshu Kuai, Ali Harakeh, Liam Paull, Steven L. Waslander
However, image-to point representation learning for autonomous driving datasets faces two main challenges: 1) the abundance of self-similarity, which results in the contrastive losses pushing away semantically similar point and image regions and thus disturbing the local semantic structure of the learned representations, and 2) severe class imbalance as pretraining gets dominated by over-represented classes.
no code implementations • 24 Nov 2022 • Ali Harakeh, Jordan Hu, Naiqing Guan, Steven L. Waslander, Liam Paull
A common approach to model uncertainty is to choose a parametric distribution and fit the data to it using maximum likelihood estimation.
no code implementations • 29 Jul 2021 • John Willes, James Harrison, Ali Harakeh, Chelsea Finn, Marco Pavone, Steven Waslander
As autonomous decision-making agents move from narrow operating environments to unstructured worlds, learning systems must move from a closed-world formulation to an open-world and few-shot setting in which agents continuously learn new classes from small amounts of information.
2 code implementations • CVPR 2021 • Cody Reading, Ali Harakeh, Julia Chae, Steven L. Waslander
We validate our approach on the KITTI 3D object detection benchmark, where we rank 1st among published monocular methods.
3 code implementations • 13 Jan 2021 • Ali Harakeh, Steven L. Waslander
We show that in the context of object detection, training variance networks with negative log likelihood (NLL) can lead to high entropy predictive distributions regardless of the correctness of the output mean.
no code implementations • ICLR 2021 • Ali Harakeh, Steven L. Waslander
We show that in the context of object detection, training variance networks with negative log likelihood (NLL) can lead to high entropy predictive distributions regardless of the correctness of the output mean.
1 code implementation • 20 Nov 2020 • Di Feng, Ali Harakeh, Steven Waslander, Klaus Dietmayer
Next, we present a strict comparative study for probabilistic object detection based on an image detector and three public autonomous driving datasets.
2 code implementations • 9 Mar 2019 • Ali Harakeh, Michael Smart, Steven L. Waslander
When incorporating deep neural networks into robotic systems, a major challenge is the lack of uncertainty measures associated with their output predictions.
no code implementations • 16 Jul 2018 • Jungwook Lee, Sean Walsh, Ali Harakeh, Steven L. Waslander
Training 3D object detectors for autonomous driving has been limited to small datasets due to the effort required to generate annotations.
no code implementations • 16 Jul 2018 • Matt Angus, Mohamed ElBalkini, Samin Khan, Ali Harakeh, Oles Andrienko, Cody Reading, Steven Waslander, Krzysztof Czarnecki
Utilizing open-source tools and resources found in single-player modding communities, we provide a method for persistent, ground truth, asset annotation of a game world.
2 code implementations • 20 Jun 2018 • Alex D. Pon, Oles Andrienko, Ali Harakeh, Steven L. Waslander
The root cause of this issue is that no public dataset contains both traffic light and sign labels, which leads to difficulties in developing a joint detection framework.
2 code implementations • 31 Jan 2018 • Jason Ku, Ali Harakeh, Steven L. Waslander
With the rise of data driven deep neural networks as a realization of universal function approximators, most research on computer vision problems has moved away from hand crafted classical image processing algorithms.
4 code implementations • 6 Dec 2017 • Jason Ku, Melissa Mozifian, Jungwook Lee, Ali Harakeh, Steven Waslander
We present AVOD, an Aggregate View Object Detection network for autonomous driving scenarios.
no code implementations • CVPR 2016 • Ali Harakeh, Daniel Asmar, Elie Shammas
This paper proposes a novel technique to extract training data from free space in a scene using a stereo camera.