Related papers: LoopDA: Constructing Self-loops to Adapt Nighttime…
Semantic scene understanding is crucial for robotics and computer vision applications. In autonomous driving, 3D semantic segmentation plays an important role for enabling safe navigation. Despite significant advances in the field, the…
Solving the domain shift problem during inference is essential in medical imaging, as most deep-learning based solutions suffer from it. In practice, domain shifts are tackled by performing Unsupervised Domain Adaptation (UDA), where a…
Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly…
Test-time adaptation (TTA) aims to adapt a pre-trained model to a new test domain without access to source data after deployment. Existing approaches typically rely on self-training with pseudo-labels since ground-truth cannot be obtained…
Autonomous vehicles clearly benefit from the expanded Field of View (FoV) of 360-degree sensors, but modern semantic segmentation approaches rely heavily on annotated training data which is rarely available for panoramic images. We look at…
3D object detectors are fundamental components of perception systems in autonomous vehicles. While these detectors achieve remarkable performance on standard autonomous driving benchmarks, they often struggle to generalize across different…
In this paper, we tackle the unsupervised domain adaptation (UDA) for semantic segmentation, which aims to segment the unlabeled real data using labeled synthetic data. The main problem of UDA for semantic segmentation relies on reducing…
This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…
Although data is abundant, data labeling is expensive. Semi-supervised learning methods combine a few labeled samples with a large corpus of unlabeled data to effectively train models. This paper introduces our proposed method LiDAM, a…
Monocular depth estimation (MDE) has attracted intense study due to its low cost and critical functions for robotic tasks such as localization, mapping and obstacle detection. Supervised approaches have led to great success with the advance…
Acquiring labeled 6D poses from real images is an expensive and time-consuming task. Though massive amounts of synthetic RGB images are easy to obtain, the models trained on them suffer from noticeable performance degradation due to the…
Instance segmentation is crucial for autonomous driving, but is hindered by the lack of annotated real-world data due to expensive labeling costs. Unsupervised Domain Adaptation (UDA) offers a solution by transferring knowledge from labeled…
In autonomous driving, 3D LiDAR plays a crucial role in understanding the vehicle's surroundings. However, the newly emerged, unannotated objects presents few-shot learning problem for semantic segmentation. This paper addresses the…
The ability to scene understanding in adverse visual conditions, e.g., nighttime, has sparked active research for RGB-Thermal (RGB-T) semantic segmentation. However, it is essentially hampered by two critical problems: 1) the day-night gap…
Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to…
Semantic segmentation models based on convolutional neural networks have recently displayed remarkable performance for a multitude of applications. However, these models typically do not generalize well when applied on new domains,…
Annotating large scale datasets to train modern convolutional neural networks is prohibitively expensive and time-consuming for many real tasks. One alternative is to train the model on labeled synthetic datasets and apply it in the real…
Semantic segmentation of 3D geospatial point clouds is fundamental to remote sensing applications, yet domain shifts caused by regional and acquisition-related variations often degrade model performance. Although domain adaptation can…
Deep neural networks have been widely studied in autonomous driving applications such as semantic segmentation or depth estimation. However, training a neural network in a supervised manner requires a large amount of annotated labels which…
Universal domain adaptation (UniDA) transfers knowledge from a labeled source domain to an unlabeled target domain, where label spaces may differ and the target domain may contain private classes. Previous UniDA methods primarily focused on…