Related papers: Panoptic Feature Pyramid Networks
The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations: (1) their optimal depth is apriori unknown, requiring…
Building segmentation is of great importance in the task of remote sensing imagery interpretation. However, the existing semantic segmentation and instance segmentation methods often lead to segmentation masks with blurred boundaries. In…
Panoptic Narrative Detection (PND) and Segmentation (PNS) are two challenging tasks that involve identifying and locating multiple targets in an image according to a long narrative description. In this paper, we propose a unified and…
Pursuing more complete and coherent scene understanding towards realistic vision applications drives edge detection from category-agnostic to category-aware semantic level. However, finer delineation of instance-level boundaries still…
Scene text detection methods based on deep learning have achieved remarkable results over the past years. However, due to the high diversity and complexity of natural scenes, previous state-of-the-art text detection methods may still…
For complex segmentation tasks, fully automatic systems are inherently limited in their achievable accuracy for extracting relevant objects. Especially in cases where only few data sets need to be processed for a highly accurate result,…
Recently, there is growing attention on one-stage panoptic segmentation methods which aim to segment instances and stuff jointly within a fully convolutional pipeline efficiently. However, most of the existing works directly feed the…
Semantic segmentation is challenging as it requires both object-level information and pixel-level accuracy. Recently, FCN-based systems gained great improvement in this area. Unlike classification networks, combining features of different…
Object instance segmentation is one of the most fundamental but challenging tasks in computer vision, and it requires the pixel-level image understanding. Most existing approaches address this problem by adding a mask prediction branch to a…
Weakly-supervised instance segmentation, which could greatly save labor and time cost of pixel mask annotation, has attracted increasing attention in recent years. The commonly used pipeline firstly utilizes conventional image segmentation…
The objective of this work is to explore how to effectively and efficiently adapt pre-trained visual foundation models to various downstream tasks of semantic segmentation. Previous methods usually fine-tuned the entire networks for each…
Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to generalize to unseen object categories. Few-shot segmentation…
Multi-task and multi-domain learning methods seek to learn multiple tasks/domains, jointly or one after another, using a single unified network. The primary challenge and opportunity lie in leveraging shared information across these tasks…
In this paper, we introduce a novel network that generates semantic, instance, and part segmentation using a shared encoder and effectively fuses them to achieve panoptic-part segmentation. Unifying these three segmentation problems allows…
State-of-the-art systems for semantic image segmentation use feed-forward pipelines with fixed computational costs. Building an image segmentation system that works across a range of computational budgets is challenging and time-intensive…
Panoptic segmentation assigns semantic and instance ID labels to every pixel of an image. As permutations of instance IDs are also valid solutions, the task requires learning of high-dimensional one-to-many mapping. As a result,…
Semantic, instance, and panoptic segmentation of 3D point clouds have been addressed using task-specific models of distinct design. Thereby, the similarity of all segmentation tasks and the implicit relationship between them have not been…
Tremendous efforts have been made to improve mask localization accuracy in instance segmentation. Modern instance segmentation methods relying on fully convolutional networks perform pixel-wise classification, which ignores object…
Multi-scale deep CNNs have been used successfully for problems mapping each pixel to a label, such as depth estimation and semantic segmentation. It has also been shown that such architectures are reusable and can be used for multiple…
This paper presents GridNet, a new Convolutional Neural Network (CNN) architecture for semantic image segmentation (full scene labelling). Classical neural networks are implemented as one stream from the input to the output with subsampling…