Related papers: Condition-Invariant Semantic Segmentation
Deep superpixel algorithms have made remarkable strides by substituting hand-crafted features with learnable ones. Nevertheless, we observe that existing deep superpixel methods, serving as mid-level representation operations, remain…
We focus on Unsupervised Domain Adaptation (UDA) for the task of semantic segmentation. Recently, adversarial alignment has been widely adopted to match the marginal distribution of feature representations across two domains globally.…
Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a semantic layout is used to generate a photorealistic image. State-of-the-art conditional Generative Adversarial Networks (GANs) need a huge amount of paired…
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 exemplar-based style synthesis…
Domain adaptive semantic segmentation aims to train a model performing satisfactory pixel-level predictions on the target with only out-of-domain (source) annotations. The conventional solution to this task is to minimize the discrepancy…
Scene-agnostic visual inpainting remains very challenging despite progress in patch-based methods. Recently, Pathak et al. 2016 have introduced convolutional "context encoders" (CEs) for unsupervised feature learning through image…
Due to the scarcity of dense pixel-level semantic annotations for images recorded in adverse visual conditions, there has been a keen interest in unsupervised domain adaptation (UDA) for the semantic segmentation of such images. UDA adapts…
Semantic image editing requires inpainting pixels following a semantic map. It is a challenging task since this inpainting requires both harmony with the context and strict compliance with the semantic maps. The majority of the previous…
Cloud segmentation plays a crucial role in image analysis for climate modeling. Manually labeling the training data for cloud segmentation is time-consuming and error-prone. We explore to train segmentation networks with synthetic data due…
Unsupervised domain adaptation is a promising technique for semantic segmentation and other computer vision tasks for which large-scale data annotation is costly and time-consuming. In semantic segmentation, it is attractive to train models…
Unsupervised domain adaptive semantic segmentation (UDA-SS) aims to train a model on the source domain data (e.g., synthetic) and adapt the model to predict target domain data (e.g., real-world) without accessing target annotation data.…
Unsupervised domain adaptation for semantic segmentation has been intensively studied due to the low cost of the pixel-level annotation for synthetic data. The most common approaches try to generate images or features mimicking the…
Although Domain Adaptation in Semantic Scene Segmentation has shown impressive improvement in recent years, the fairness concerns in the domain adaptation have yet to be well defined and addressed. In addition, fairness is one of the most…
In few-shot unsupervised domain adaptation (FS-UDA), most existing methods followed the few-shot learning (FSL) methods to leverage the low-level local features (learned from conventional convolutional models, e.g., ResNet) for…
Since the fully convolutional network has achieved great success in semantic segmentation, lots of works have been proposed focusing on extracting discriminative pixel feature representations. However, we observe that existing methods still…
Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading approach is consistency regularization by selftraining with…
We propose a novel method that tackles the problem of unsupervised domain adaptation for semantic segmentation by maximizing the cosine similarity between the source and the target domain at the feature level. A segmentation network mainly…
Recent advances in unsupervised domain adaptation for semantic segmentation have shown great potentials to relieve the demand of expensive per-pixel annotations. However, most existing works address the domain discrepancy by aligning the…
Semantic segmentation of remote sensing (RS) images is a challenging yet essential task with broad applications. While deep learning, particularly supervised learning with large-scale labeled datasets, has significantly advanced this field,…
State-of-the-art semantic segmentation models are typically optimized in a data-driven fashion, minimizing solely per-pixel or per-segment classification objectives on their training data. This purely data-driven paradigm often leads to…