Related papers: RobustNet: Improving Domain Generalization in Urba…
Traditional domain generalization methods often rely on domain alignment to reduce inter-domain distribution differences and learn domain-invariant representations. However, domain shifts are inherently difficult to eliminate, which limits…
We propose to harness the potential of simulation for the semantic segmentation of real-world self-driving scenes in a domain generalization fashion. The segmentation network is trained without any data of target domains and tested on the…
Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data…
Autonomous vehicles and driving systems use scene parsing as an essential tool to understand the surrounding environment. Panoptic segmentation is a state-of-the-art technique which proves to be pivotal in this use case. Deep learning-based…
This paper exploits the intrinsic features of urban-scene images and proposes a general add-on module, called height-driven attention networks (HANet), for improving semantic segmentation for urban-scene images. It emphasizes informative…
Comprehensive semantic segmentation is one of the key components for robust scene understanding and a requirement to enable autonomous driving. Driven by large scale datasets, convolutional neural networks show impressive results on this…
Shadow removal from a single image is generally still an open problem. Most existing learning-based methods use supervised learning and require a large number of paired images (shadow and corresponding non-shadow images) for training. A…
The generalization with respect to domain shifts, as they frequently appear in applications such as autonomous driving, is one of the remaining big challenges for deep learning models. Therefore, we propose an intra-source style…
In the field of computer vision, the persistent presence of color bias, resulting from fluctuations in real-world lighting and camera conditions, presents a substantial challenge to the robustness of models. This issue is particularly…
Convolutional Neural Networks (CNNs) often fail to maintain their performance when they confront new test domains, which is known as the problem of domain shift. Recent studies suggest that one of the main causes of this problem is CNNs'…
Robust lane detection is essential for advanced driver assistance and autonomous driving, yet models trained on public datasets such as CULane often fail to generalise across different camera viewpoints. This paper addresses the challenge…
We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. During training, our…
Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios. We argue that the feature statistics (mean and standard…
While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…
During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving. However, to train CNNs requires a considerable…
Semantic segmentation in a supervised learning manner has achieved significant progress in recent years. However, its performance usually drops dramatically due to the data-distribution discrepancy between seen and unseen domains when we…
Open-set single-source domain generalization aims to use a single-source domain to learn a robust model that can be generalized to unknown target domains with both domain shifts and label shifts. The scarcity of the source domain and the…
This paper introduces a concept of neural network specialization via task-specific domain constraining, aimed at enhancing network performance on data subspace in which the network operates. The study presents experiments on training…
Deep learning models usually suffer from domain shift issues, where models trained on one source domain do not generalize well to other unseen domains. In this work, we investigate the single-source domain generalization problem: training a…
Nighttime semantic segmentation plays a crucial role in practical applications, such as autonomous driving, where it frequently encounters difficulties caused by inadequate illumination conditions and the absence of well-annotated datasets.…