Related papers: Style-Hallucinated Dual Consistency Learning for D…
In semantic image synthesis the state of the art is dominated by methods that use customized variants of the SPatially-Adaptive DE-normalization (SPADE) layers, which allow for good visual generation quality and editing versatility. By…
Using synthetic data for training neural networks that achieve good performance on real-world data is an important task as it can reduce the need for costly data annotation. Yet, synthetic and real world data have a domain gap. Reducing…
Deep learning-based methods have made significant achievements for image dehazing. However, most of existing dehazing networks are concentrated on training models using simulated hazy images, resulting in generalization performance…
Recently, the progress of learning-by-synthesis has proposed a training model for synthetic images, which can effectively reduce the cost of human and material resources. However, due to the different distribution of synthetic images…
Semantic segmentation provides pixel-level scene understanding essential for autonomous driving and fine-grained perception tasks. However, training segmentation models requires costly, labor-intensive annotations on real-world datasets.…
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…
Semantic segmentation of various tissue and nuclei types in histology images is fundamental to many downstream tasks in the area of computational pathology (CPath). In recent years, Deep Learning (DL) methods have been shown to perform well…
Domain Generalization (DG) is a challenging task in machine learning that requires a coherent ability to comprehend shifts across various domains through extraction of domain-invariant features. DG performance is typically evaluated by…
Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a source domain to a new target domain where no labelled data is available. In this work, we investigate the problem of UDA from a synthetic computer-generated domain to a…
Change detection has essential significance for the region's development, in which pseudo-changes between bitemporal images induced by imaging environmental factors are key challenges. Existing transformation-based methods regard…
As synthetic imagery is used more frequently in training deep models, it is important to understand how different synthesis techniques impact the performance of such models. In this work, we perform a thorough evaluation of the…
Fine-grained domain generalization (FGDG) aims to learn a fine-grained representation that can be well generalized to unseen target domains when only trained on the source domain data. Compared with generic domain generalization, FGDG is…
In this paper, we present the submission to the 5th Annual Smoky Mountains Computational Sciences Data Challenge, Challenge 3. This is the solution for semantic segmentation problem in both real-world and synthetic images from a vehicle s…
Semantic image segmentation is a central and challenging task in autonomous driving, addressed by training deep models. Since this training draws to a curse of human-based image labeling, using synthetic images with automatically generated…
The supervised training of deep networks for semantic segmentation requires a huge amount of labeled real world data. To solve this issue, a commonly exploited workaround is to use synthetic data for training, but deep networks show a…
As a recent noticeable topic, domain generalization (DG) aims to first learn a generic model on multiple source domains and then directly generalize to an arbitrary unseen target domain without any additional adaption. In previous DG…
Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from…
In this paper, we consider the problem of domain generalization in semantic segmentation, which aims to learn a robust model using only labeled synthetic (source) data. The model is expected to perform well on unseen real (target) domains.…
Existing research based on deep learning has extensively explored the problem of daytime image dehazing. However, few studies have considered the characteristics of nighttime hazy scenes. There are two distinctions between nighttime and…
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…