Related papers: Bidirectional Self-Training with Multiple Anisotro…

Segmentation is a crucial analysis task in biomedical imaging. Given the diverse experimental settings in this field, the lack of generalization limits the use of deep learning in practice. Domain adaptation is a promising remedy: it…

Semantic segmentation has been continuously investigated in the last ten years, and majority of the established technologies are based on supervised models. In recent years, image-level weakly supervised semantic segmentation (WSSS),…

Domain adaptation solves image classification problems in the target domain by taking advantage of the labelled source data and unlabelled target data. Usually, the source and target domains share the same set of classes. As a special case,…

Few-shot segmentation aims at assigning a category label to each image pixel with few annotated samples. It is a challenging task since the dense prediction can only be achieved under the guidance of latent features defined by sparse…

Semantic segmentation networks, which are essential for robotic perception, often suffer from performance degradation when the visual distribution of the deployment environment differs from that of the source dataset on which they were…

Categories can be represented at different levels of abstraction, from prototypes focused on the most typical members to remembering all observed exemplars of the category. These representations have been explored in the context of…

In contrast to a standard closed-set domain adaptation task, partial domain adaptation setup caters to a realistic scenario by relaxing the identical label set assumption. The fact of source label set subsuming the target label set,…

Recently, deep neural networks have greatly advanced histopathology image segmentation but usually require abundant annotated data. However, due to the gigapixel scale of whole slide images and pathologists' heavy daily workload, obtaining…

Self-training via pseudo labeling is a conventional, simple, and popular pipeline to leverage unlabeled data. In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via…

Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to unseen image domains. As the labeling process is tedious and labor intensive,…

Unsupervised domain adaptation for semantic segmentation aims to make models trained on synthetic data (source domain) adapt to real images (target domain). Previous feature-level adversarial learning methods only consider adapting models…

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…

Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models by weak labels, which is receiving significant attention due to its low annotation cost. Existing approaches focus on generating pseudo labels for supervision…

Road segmentation from remote sensing images is a challenging task with wide ranges of application potentials. Deep neural networks have advanced this field by leveraging the power of large-scale labeled data, which, however, are extremely…

Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels.…

Domain adaptive semantic segmentation attempts to make satisfactory dense predictions on an unlabeled target domain by utilizing the supervised model trained on a labeled source domain. In this work, we propose Semantic-Guided Pixel…

Despite recent advances in semantic segmentation, an inevitable challenge is the performance degradation caused by the domain shift in real applications. Current dominant approach to solve this problem is unsupervised domain adaptation…

Self-training based on pseudo-labels has emerged as a dominant approach for addressing conditional distribution shifts in unsupervised domain adaptation (UDA) for semantic segmentation problems. A notable drawback, however, is that this…

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,…

Unsupervised source-free domain adaptation methods aim to train a model for the target domain utilizing a pretrained source-domain model and unlabeled target-domain data, particularly when accessibility to source data is restricted due to…