Active learning is a label-efficient machine learning method that actively selects the most
valuable unlabeled samples to annotate. Active learning focuses on achieving the best …

As artificial intelligence (AI) has already seen numerous successful applications, the
upcoming challenge lies in how to realize artificial general intelligence (AGI). Self-learning …

Active learning strategies for 3D object detection in autonomous driving datasets may help
to address challenges of data imbalance, redundancy, and high-dimensional data. We …

The curation of large-scale datasets is still costly and requires much time and resources.
Data is often manually labeled, and the challenge of creating high-quality datasets remains …

Rapid advances in Machine Learning (ML) have triggered new trends in Autonomous
Vehicles (AVs). ML algorithms play a crucial role in interpreting sensor data, predicting …

End-to-end differentiable learning for autonomous driving (AD) has recently become a
prominent paradigm. One main bottleneck lies in its voracious appetite for high-quality …

In practical object detection computer vision applications, training commonly incorporates
multiple data sources. Domain adaptation enhances the models' capacity to generalize …

Recent aerial object detection models rely on a large amount of labeled training data, which
requires unaffordable manual labeling costs in large aerial scenes with dense objects …

The ability of deep learning methods to perform classification and regression tasks relies
heavily on their capacity to uncover manifolds in high-dimensional data spaces and project …

Active learning strives to reduce the need for costly data annotation, by repeatedly querying
an annotator to label the most informative samples from a pool of unlabeled data, and then …