相关论文: SelfD: Self-Learning Large-Scale Driving Policies …

Automatic pseudo-labeling is a powerful tool to tap into large amounts of sequential unlabeled data. It is specially appealing in safety-critical applications of autonomous driving, where performance requirements are extreme, datasets are…

Finetuning a large vision language model (VLM) on a target dataset after large scale pretraining is a dominant paradigm in visual question answering (VQA). Datasets for specialized tasks such as knowledge-based VQA or VQA in non…

Monocular 3D object detection plays a crucial role in autonomous driving. However, existing monocular 3D detection algorithms depend on 3D labels derived from LiDAR measurements, which are costly to acquire for new datasets and challenging…

Achieving fully autonomous driving systems requires learning rational decisions in a wide span of scenarios, including safety-critical and out-of-distribution ones. However, such cases are underrepresented in real-world corpus collected by…

Current 3D semi-supervised segmentation methods face significant challenges such as limited consideration of contextual information and the inability to generate reliable pseudo-labels for effective unsupervised data use. To address these…

In order to train robust deep learning models, large amounts of labelled data is required. However, in the absence of such large repositories of labelled data, unlabeled data can be exploited for the same. Semi-Supervised learning aims to…

Training neural networks to perform 3D object detection for autonomous driving requires a large amount of diverse annotated data. However, obtaining training data with sufficient quality and quantity is expensive and sometimes impossible…

In response to the growing demand for 3D object detection in applications such as autonomous driving, robotics, and augmented reality, this work focuses on the evaluation of semi-supervised learning approaches for point cloud data. The…

Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…

Semi-supervised learning (SSL) has been proposed to leverage unlabeled data for training powerful models when only limited labeled data is available. While existing SSL methods assume that samples in the labeled and unlabeled data share the…

The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-model (LM) pretraining, how we can make the best use of U is…

While deep learning strategies achieve outstanding results in computer vision tasks, one issue remains: The current strategies rely heavily on a huge amount of labeled data. In many real-world problems, it is not feasible to create such an…

Understanding world dynamics is crucial for planning in autonomous driving. Recent methods attempt to achieve this by learning a 3D occupancy world model that forecasts future surrounding scenes based on current observation. However, 3D…

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 promising accuracy but are prone to over-fit to domain…

Self-training, a semi-supervised learning algorithm, leverages a large amount of unlabeled data to improve learning when the labeled data are limited. Despite empirical successes, its theoretical characterization remains elusive. To the…

Understanding the scene is key for autonomously navigating vehicles and the ability to segment the surroundings online into moving and non-moving objects is a central ingredient for this task. Often, deep learning-based methods are used to…

In this paper, a multi-modal data based semi-supervised learning (SSL) framework that jointly use channel state information (CSI) data and RGB images for vehicle positioning is designed. In particular, an outdoor positioning system where…

Autonomous driving relies on a huge volume of real-world data to be labeled to high precision. Alternative solutions seek to exploit driving simulators that can generate large amounts of labeled data with a plethora of content variations.…

Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and in turn teach itself. To obtain valid supervision, active…

Estimating the traversability of terrain should be reliable and accurate in diverse conditions for autonomous driving in off-road environments. However, learning-based approaches often yield unreliable results when confronted with…