Intelligent vehicles (IVs) have gained worldwide attention due to their increased
convenience, safety advantages, and potential commercial value. Despite predictions of …

In this paper we describe the design and the ideas motivating a new Continual Learning
benchmark for Autonomous Driving (CLAD), that focuses on the problems of object …

With the rise of deep convolutional neural networks, object detection has achieved
prominent advances in past years. However, such prosperity could not camouflage the …

Abstract Domain adaptation is crucial to adapt a learned model to new scenarios, such as
domain shifts or changing data distributions. Current approaches usually require a large …

Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks
via randomly masking image patches and reconstruction. However, effective data …

Multimodal large language models (MLLMs) have shown impressive reasoning abilities.
However, they are also more vulnerable to jailbreak attacks than their LLM predecessors …

Although deep neural networks enable impressive visual perception performance for
autonomous driving, their robustness to varying weather conditions still requires attention …

Contemporary deep-learning object detection methods for autonomous driving usually
presume fixed categories of common traffic participants, such as pedestrians and cars. Most …

Recent advancements in diffusion models have significantly enhanced the data synthesis
with 2D control. Yet, precise 3D control in street view generation, crucial for 3D perception …

Continual learning needs to overcome catastrophic forgetting of the past. Memory replay of
representative old training samples has been shown as an effective solution, and achieves …