Related papers: Self-Regularized Prototypical Network for Few-Shot…

This work considers semi-supervised segmentation as a dense prediction problem based on prototype vector correlation and proposes a simple way to represent each segmentation class with multiple prototypes. To avoid degenerate solutions, two…

Accurate segmentation of lesions plays a critical role in medical image analysis and diagnosis. Traditional segmentation approaches that rely solely on visual features often struggle with the inherent uncertainty in lesion distribution and…

Recent years have seen a rapid growth in new approaches improving the accuracy of semantic segmentation in a weakly supervised setting, i.e. with only image-level labels available for training. However, this has come at the cost of…

Learning with limited labelled data is a challenging problem in various applications, including remote sensing. Few-shot semantic segmentation is one approach that can encourage deep learning models to learn from few labelled examples for…

Few-shot segmentation models excel in metal defect detection due to their rapid generalization ability to new classes and pixel-level segmentation, rendering them ideal for addressing data scarcity issues and achieving refined object…

For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions. Recently, convolutional neural networks…

3D point cloud semantic segmentation aims to group all points into different semantic categories, which benefits important applications such as point cloud scene reconstruction and understanding. Existing supervised point cloud semantic…

Prototype learning is extensively used for few-shot segmentation. Typically, a single prototype is obtained from the support feature by averaging the global object information. However, using one prototype to represent all the information…

Deep Neural Networks (DNNs) have recently shown state of the art performance on semantic segmentation tasks, however, they still suffer from problems of poor boundary localization and spatial fragmented predictions. The difficulties lie in…

Few-shot point cloud semantic segmentation aims to train a model to quickly adapt to new unseen classes with only a handful of support set samples. However, the noise-free assumption in the support set can be easily violated in many…

Medical image segmentation is one of the domains where sufficient annotated data is not available. This necessitates the application of low-data frameworks like few-shot learning. Contemporary prototype-based frameworks often do not account…

Few-shot remote sensing image classification is challenging due to limited labeled samples and high variability in land-cover types. We propose a reconstruction-guided few-shot network (RGFS-Net) that enhances generalization to unseen…

The potential for augmenting the segmentation of brain tumors through the use of few-shot learning is vast. Although several deep learning networks (DNNs) demonstrate promising results in terms of segmentation, they require a substantial…

While deep learning has been successfully applied to many real-world computer vision tasks, training robust classifiers usually requires a large amount of well-labeled data. However, the annotation is often expensive and time-consuming.…

Semantic segmentation, vital for applications ranging from autonomous driving to robotics, faces significant challenges in domains where collecting large annotated datasets is difficult or prohibitively expensive. In such contexts, such as…

We tackle a novel few-shot learning challenge, which we call few-shot semantic edge detection, aiming to localize crisp boundaries of novel categories using only a few labeled samples. We also present a Class-Agnostic Few-shot Edge…

Few-shot segmentation (FSS) expects models trained on base classes to work on novel classes with the help of a few support images. However, when there exists a domain gap between the base and novel classes, the state-of-the-art FSS methods…

Traditional semantic segmentation tasks require a large number of labels and are difficult to identify unlearned categories. Few-shot semantic segmentation (FSS) aims to use limited labeled support images to identify the segmentation of new…

Few-shot semantic segmentation (FSS) is a crucial challenge in computer vision, driving extensive research into a diverse range of methods, from advanced meta-learning techniques to simple transfer learning baselines. With the emergence of…

Understanding visual scenes relies more and more on dense pixel-wise classification obtained via deep fully convolutional neural networks. However, due to the nature of the networks, predictions often suffer from blurry boundaries and…