Related papers: Bidirectional Self-Training with Multiple Anisotro…
Self-supervised learning approaches for unsupervised domain adaptation (UDA) of semantic segmentation models suffer from challenges of predicting and selecting reasonable good quality pseudo labels. In this paper, we propose a novel…
Semantic segmentation models only perform well on the domain they are trained on and datasets for training are scarce and often have a small label-spaces, because the pixel level annotations required are expensive to make. Thus training…
Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we propose a novel multi-source domain adaptation framework based on…
Unsupervised domain adaptation (UDA) becomes more and more popular in tackling real-world problems without ground truth of the target domain. Though tedious annotation work is not required, UDA unavoidably faces two problems: 1) how to…
Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training. Additionally, such models do not generalise well to environments where the statistical…
Domain adaptive semantic segmentation enables robust pixel-wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in…
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,…
Semantic segmentation is essential for comprehending images, but the process necessitates a substantial amount of detailed annotations at the pixel level. Acquiring such annotations can be costly in the real-world. Unsupervised domain…
It is desirable to transfer the knowledge stored in a well-trained source model onto non-annotated target domain in the absence of source data. However, state-of-the-art methods for source free domain adaptation (SFDA) are subject to strict…
Self-training emerges as an important research line on domain adaptation. By taking the model's prediction as the pseudo labels of the unlabeled data, self-training bootstraps the model with pseudo instances in the target domain. However,…
Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we…
Source-free domain adaptation has developed rapidly in recent years, where the well-trained source model is adapted to the target domain instead of the source data, offering the potential for privacy concerns and intellectual property…
Mixup-based data augmentation has been validated to be a critical stage in the self-training framework for unsupervised domain adaptive semantic segmentation (UDA-SS), which aims to transfer knowledge from a well-annotated (source) domain…
Recent advances in unsupervised domain adaptation have seen considerable progress in semantic segmentation. Existing methods either align different domains with adversarial training or involve the self-learning that utilizes pseudo labels…
We study unsupervised domain adaptation (UDA) for semantic segmentation. Currently, a popular UDA framework lies in self-training which endows the model with two-fold abilities: (i) learning reliable semantics from the labeled images in the…
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…
Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. Leveraging the supervision from auxiliary tasks~(such as depth estimation) has the…
3D object detection networks tend to be biased towards the data they are trained on. Evaluation on datasets captured in different locations, conditions or sensors than that of the training (source) data results in a drop in model…
Semantic segmentation algorithms require access to well-annotated datasets captured under diverse illumination conditions to ensure consistent performance. However, poor visibility conditions at varying illumination conditions result in…
Semantic segmentation requires extensive pixel-level annotation, motivating unsupervised domain adaptation (UDA) to transfer knowledge from labelled source domains to unlabelled or weakly labelled target domains. One of the most efficient…