Related papers: The Why, When, and How to Use Active Learning in L…
This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D…
Accurate motion understanding of the dynamic objects within the scene in bird's-eye-view (BEV) is critical to ensure a reliable obstacle avoidance system and smooth path planning for autonomous vehicles. However, this task has received…
Accurate identification of important objects in the scene is a prerequisite for safe and high-quality decision making and motion planning of intelligent agents (e.g., autonomous vehicles) that navigate in complex and dynamic environments.…
Uncertainty estimation is crucial in safety-critical settings such as automated driving as it provides valuable information for several downstream tasks including high-level decision making and path planning. In this work, we propose…
Active learning enables efficient model training by leveraging interactions between machine learning agents and human annotators. We study and propose a novel framework that formulates batch active learning from the sparse approximation's…
3D object detection is an essential task for computer vision applications in autonomous vehicles and robotics. However, models often struggle to quantify detection reliability, leading to poor performance on unfamiliar scenes. We introduce…
Object detection through either RGB images or the LiDAR point clouds has been extensively explored in autonomous driving. However, it remains challenging to make these two data sources complementary and beneficial to each other. In this…
Label aggregation such as majority voting is commonly used to resolve annotator disagreement in dataset creation. However, this may disregard minority values and opinions. Recent studies indicate that learning from individual annotations…
Supervised machine learning relies on the availability of good labelled data for model training. Labelled data is acquired by human annotation, which is a cumbersome and costly process, often requiring subject matter experts. Active…
We conduct a comprehensive evaluation of state-of-the-art deep active learning methods. Surprisingly, under general settings, no single-model method decisively outperforms entropy-based active learning, and some even fall short of random…
Convolutional Neural Networks achieve state-of-the-art accuracy in object detection tasks. However, they have large computational and energy requirements that challenge their deployment on resource-constrained edge devices. Object detection…
3D object detection with surround-view images is an essential task for autonomous driving. In this work, we propose DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D object detection in…
Object detection plays a critical role in autonomous driving, where accurately and efficiently detecting objects in fast-moving scenes is crucial. Traditional frame-based cameras face challenges in balancing latency and bandwidth,…
Active learning as a paradigm in deep learning is especially important in applications involving intricate perception tasks such as object detection where labels are difficult and expensive to acquire. Development of active learning methods…
Although modern object detection and classification models achieve high accuracy, these are typically constrained in advance on a fixed train set and are therefore not flexible to deal with novel, unseen object categories. Moreover, these…
In supervised learning, acquiring labeled training data for a predictive model can be very costly, but acquiring a large amount of unlabeled data is often quite easy. Active learning is a method of obtaining predictive models with high…
3D object trackers usually require training on large amounts of annotated data that is expensive and time-consuming to collect. Instead, we propose leveraging vast unlabeled datasets by self-supervised metric learning of 3D object trackers,…
3D semantic occupancy prediction aims to forecast detailed geometric and semantic information of the surrounding environment for autonomous vehicles (AVs) using onboard surround-view cameras. Existing methods primarily focus on intricate…
Applying pseudo labeling techniques has been found to be advantageous in semi-supervised 3D object detection (SSOD) in Bird's-Eye-View (BEV) for autonomous driving, particularly where labeled data is limited. In the literature, Exponential…
3D perception based on the representations learned from multi-camera bird's-eye-view (BEV) is trending as cameras are cost-effective for mass production in autonomous driving industry. However, there exists a distinct performance gap…