We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised
domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D …

Deep learning-based object detectors have shown remarkable improvements. However,
supervised learning-based methods perform poorly when the train data and the test data …

In this paper, we present a self-training method, named ST3D++, with a holistic pseudo label
denoising pipeline for unsupervised domain adaptation on 3D object detection. ST3D++ …

Deep Neural Networks (DNNs) often rely on vast datasets for training. Given the large size of
such datasets, it is conceivable that they contain specific samples that either do not …

Salient objects attract human attention and usually stand out clearly from their surroundings.
In contrast, camouflaged objects share similar colors or textures with the environment. In this …

Deep neural networks can be roughly divided into deterministic neural networks and
stochastic neural networks. The former is usually trained to achieve a mapping from input …

Training a semantic segmentation model requires a large amount of pixel-level annotation,
hampering its application at scale. With computer graphics, we can generate almost …

Image semantic segmentation is a basic and challenging computer vision task, where each
pixel in an image is classified into a semantic class. In recent years, deep neural networks …

Self-driving cars must detect other vehicles and pedestrians in 3D to plan safe routes and
avoid collisions. State-of-the-art 3D object detectors, based on deep learning, have shown …

Deep learning has greatly advanced the performance of semantic segmentation, however,
its success relies on the availability of large amounts of annotated data for training. Hence …