Related papers: Robots Understanding Contextual Information in Hum…

Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently. Most leading WSSS…

In the 21st-century information age, with the development of big data technology, effectively extracting valuable information from massive data has become a key issue. Traditional data mining methods are inadequate when faced with…

Semantic segmentation is a challenging computer vision task demanding a significant amount of pixel-level annotated data. Producing such data is a time-consuming and costly process, especially for domains with a scarcity of experts, such as…

Semi-supervised semantic segmentation relieves the reliance on large-scale labeled data by leveraging unlabeled data. Recent semi-supervised semantic segmentation approaches mainly resort to pseudo-labeling methods to exploit unlabeled…

Automated detection and segmentation of pulmonary nodules on lung computed tomography (CT) scans can facilitate early lung cancer diagnosis. Existing supervised approaches for automated nodule segmentation on CT scans require voxel-based…

Most of the recent Deep Semantic Segmentation algorithms suffer from large generalization errors, even when powerful hierarchical representation models based on convolutional neural networks have been employed. This could be attributed to…

Compared with tedious per-pixel mask annotating, it is much easier to annotate data by clicks, which costs only several seconds for an image. However, applying clicks to learn video semantic segmentation model has not been explored before.…

Surface cracks are a common sight on public infrastructure nowadays. Recent work has been addressing this problem by supporting structural maintenance measures using machine learning methods. Those methods are used to segment surface cracks…

Universal models for medical image segmentation, such as interactive and in-context learning (ICL) models, offer strong generalization but require extensive annotations. Interactive models need repeated user prompts for each image, while…

We address the problem of weakly-supervised semantic segmentation (WSSS) using bounding box annotations. Although object bounding boxes are good indicators to segment corresponding objects, they do not specify object boundaries, making it…

Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context information, leading to…

To minimize the annotation costs associated with the training of semantic segmentation models, researchers have extensively investigated weakly-supervised segmentation approaches. In the current weakly-supervised segmentation methods, the…

We tackle open-world semantic segmentation, which aims at learning to segment arbitrary visual concepts in images, by using only image-text pairs without dense annotations. Existing open-world segmentation methods have shown impressive…

Deep learning has become a valuable tool for the automation of certain medical image segmentation tasks, significantly relieving the workload of medical specialists. Some of these tasks require segmentation to be performed on a subset of…

We propose weakly supervised language localization networks (WSLLN) to detect events in long, untrimmed videos given language queries. To learn the correspondence between visual segments and texts, most previous methods require temporal…

The success of Convolutional Neural Networks (CNNs) in 3D medical image segmentation relies on massive fully annotated 3D volumes for training that are time-consuming and labor-intensive to acquire. In this paper, we propose to annotate a…

Few-shot learning is a promising way for reducing the label cost in new categories adaptation with the guidance of a small, well labeled support set. But for few-shot semantic segmentation, the pixel-level annotations of support images are…

The costly process of obtaining semantic segmentation labels has driven research towards weakly supervised semantic segmentation (WSSS) methods, using only image-level, point, or box labels. The lack of dense scene representation requires…

Efficiently training accurate deep models for weakly supervised semantic segmentation (WSSS) with image-level labels is challenging and important. Recently, end-to-end WSSS methods have become the focus of research due to their high…

Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level…