Related papers: SqueezeSegV2: Improved Model Structure and Unsuper…

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…

Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such…

Part segmentations provide a rich and detailed part-level description of objects. However, their annotation requires an enormous amount of work, which makes it difficult to apply standard deep learning methods. In this paper, we propose the…

Visual detection of Micro Air Vehicles (MAVs) has attracted increasing attention in recent years due to its important application in various tasks. The existing methods for MAV detection assume that the training set and testing set have the…

Training robust learning algorithms across different medical imaging modalities is challenging due to the large domain gap. Unsupervised domain adaptation (UDA) mitigates this problem by using annotated images from the source domain and…

Source-free domain adaptation aims to adapt a source-trained model to an unlabeled target domain without access to the source data. It has attracted growing attention in recent years, where existing approaches focus on self-training that…

Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks. However, fine-tuning is usually computationally expensive due to the ever-growing size of pretrained models. More importantly, it may cause over-fitting…

State-of-the-art models in semantic segmentation primarily operate on single, static images, generating corresponding segmentation masks. This one-shot approach leaves little room for error correction, as the models lack the capability to…

Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification,…

Semantic segmentation is a computer vision task where classification is performed at a pixel level. Due to this, the process of labeling images for semantic segmentation is time-consuming and expensive. To mitigate this cost there has been…

While surface normals are widely used to analyse 3D scene geometry, surface normal estimation from LiDAR point clouds remains severely underexplored. This is caused by the lack of large-scale annotated datasets on the one hand, and lack of…

Multi-modal 3D semantic segmentation is vital for applications such as autonomous driving and virtual reality (VR). To effectively deploy these models in real-world scenarios, it is essential to employ cross-domain adaptation techniques…

Deep learning has significantly advanced building segmentation in remote sensing, yet models struggle to generalize on data of diverse geographic regions due to variations in city layouts and the distribution of building types, sizes and…

Domain adaptation for semantic segmentation has recently been actively studied to increase the generalization capabilities of deep learning models. The vast majority of the domain adaptation methods tackle single-source case, where the…

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 unlimited training data with precise annotation. However,a deep…

Unsupervised Domain Adaptation for semantic segmentation has gained immense popularity since it can transfer knowledge from simulation to real (Sim2Real) by largely cutting out the laborious per pixel labeling efforts at real. In this work,…

Semantic segmentation is key in autonomous driving. Using deep visual learning architectures is not trivial in this context, because of the challenges in creating suitable large scale annotated datasets. This issue has been traditionally…

Deep learning models usually require a large amount of labeled data to achieve satisfactory performance. In multimedia analysis, domain adaptation studies the problem of cross-domain knowledge transfer from a label rich source domain to a…

Birds' Eye View (BEV) semantic segmentation is an indispensable perception task in end-to-end autonomous driving systems. Unsupervised and semi-supervised learning for BEV tasks, as pivotal for real-world applications, underperform due to…

Unsupervised domain adaptation for point cloud semantic segmentation has attracted great attention due to its effectiveness in learning with unlabeled data. Most of existing methods use global-level feature alignment to transfer the…