Related papers: Finetuning Pre-trained Model with Limited Data for…

A practical shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in domain adaptation and multi-domain learning enable the learning of more domain-agnostic features, their success…

Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data. Especially for LiDAR point clouds, the domain discrepancy becomes…

Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…

LiDAR point clouds are widely used in autonomous driving and consist of large numbers of 3D points captured at high frequency to represent surrounding objects such as vehicles, pedestrians, and traffic signs. While this dense data enables…

Considerable research attention has been paid to table detection by developing not only rule-based approaches reliant on hand-crafted heuristics but also deep learning approaches. Although recent studies successfully perform table detection…

Sampling discrepancies between different manufacturers and models of lidar sensors result in inconsistent representations of objects. This leads to performance degradation when 3D detectors trained for one lidar are tested on other types of…

The need for simulated data in autonomous driving applications has become increasingly important, both for validation of pretrained models and for training new models. In order for these models to generalize to real-world applications, it…

Most object detection methods for autonomous driving usually assume a consistent feature distribution between training and testing data, which is not always the case when weathers differ significantly. The object detection model trained…

Due to the lack of large-scale labeled Thermal InfraRed (TIR) training datasets, most existing TIR trackers are trained directly on RGB datasets. However, tracking methods trained on RGB datasets suffer a significant drop-off in TIR data…

Reliable and accurate 3D object detection is a necessity for safe autonomous driving. Although LiDAR sensors can provide accurate 3D point cloud estimates of the environment, they are also prohibitively expensive for many settings.…

Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness.…

Unsupervised domain adaptation (UDA) greatly facilitates the deployment of neural networks across diverse environments. However, most state-of-the-art approaches are overly complex, relying on challenging adversarial training strategies, or…

Distributed Acoustic Sensing (DAS) technology finds growing applications across various domains. However, data distribution disparities due to heterogeneous sensing environments pose challenges for data-driven artificial intelligence (AI)…

We consider the problem of OOD generalization, where the goal is to train a model that performs well on test distributions that are different from the training distribution. Deep learning models are known to be fragile to such shifts and…

Object detection and semantic segmentation with the 3D lidar point cloud data require expensive annotation. We propose a data augmentation method that takes advantage of already annotated data multiple times. We propose an augmentation…

This work studies the semantic segmentation of 3D LiDAR data in dynamic scenes for autonomous driving applications. A system of semantic segmentation using 3D LiDAR data, including range image segmentation, sample generation, inter-frame…

We propose SampleDepth, a Convolutional Neural Network (CNN), that is suited for an adaptive LiDAR. Typically,LiDAR sampling strategy is pre-defined, constant and independent of the observed scene. Instead of letting a LiDAR sample the…

Accurate camera-LiDAR fusion relies on precise extrinsic calibration, which fundamentally depends on establishing reliable cross-modal correspondences under potentially large misalignments. Existing learning-based methods typically project…

Pretrain techniques, whether supervised or self-supervised, are widely used in deep learning to enhance model performance. In real-world clinical scenarios, different sets of magnetic resonance (MR) contrasts are often acquired for…

The labels of monocular 3D object detection (M3OD) are expensive to obtain. Meanwhile, there usually exists numerous unlabeled data in practical applications, and pre-training is an efficient way of exploiting the knowledge in unlabeled…