Representation compensation networks for continual semantic segmentation
In this work, we study the continual semantic segmentation problem, where the deep neural
networks are required to incorporate new classes continually without catastrophic forgetting …
networks are required to incorporate new classes continually without catastrophic forgetting …
Ontology matching: State of the art, future challenges, and thinking based on utilized information
X Liu, Q Tong, X Liu, Z Qin - IEEE Access, 2021 - ieeexplore.ieee.org
Information used in existing ontology matching solutions are usually grouped into four
categories: lexical information, structural information, semantic information, and external …
categories: lexical information, structural information, semantic information, and external …
Anti-aliasing semantic reconstruction for few-shot semantic segmentation
Encouraging progress in few-shot semantic segmentation has been made by leveraging
features learned upon base classes with sufficient training data to represent novel classes …
features learned upon base classes with sufficient training data to represent novel classes …
Harmonic feature activation for few-shot semantic segmentation
Few-shot semantic segmentation remains an open problem because limited support
(training) images are insufficient to represent the diverse semantics within target categories …
(training) images are insufficient to represent the diverse semantics within target categories …
Retracted: Jointly network image processing: Multi‐task image semantic segmentation of indoor scene based on CNN
L Huang, M He, C Tan, D Jiang, G Li… - IET Image …, 2020 - Wiley Online Library
Image semantic segmentation has always been a research hotspot in the field of robots. Its
purpose is to assign different semantic category labels to objects by segmenting different …
purpose is to assign different semantic category labels to objects by segmenting different …
Unboxing the black box of attention mechanisms in remote sensing big data using xai
This paper presents exploratory work looking into the effectiveness of attention mechanisms
(AMs) in improving the task of building segmentation based on convolutional neural network …
(AMs) in improving the task of building segmentation based on convolutional neural network …
Bridging the gap between semantic segmentation and instance segmentation
Fine-grained instance segmentation is considerably more complicated and challenging than
semantic segmentation. Most existing instance segmentation methods only focus on …
semantic segmentation. Most existing instance segmentation methods only focus on …
Weaklier supervised semantic segmentation with only one image level annotation per category
Image semantic segmentation tasks and methods based on weakly supervised conditions
have been proposed and achieve better and better performance in recent years. However …
have been proposed and achieve better and better performance in recent years. However …
Image segmentation using a unified Markov random field model
X Chen, C Zheng, H Yao, B Wang - IET Image Processing, 2017 - Wiley Online Library
Markov random field model (MRF) has attracted great attention in the field of image
segmentation. Its basic unit can be pixels or regions. These pixel‐based or region‐based …
segmentation. Its basic unit can be pixels or regions. These pixel‐based or region‐based …
Coarse-to-fine annotation enrichment for semantic segmentation learning
Rich high-quality annotated data is critical for semantic segmentation learning, yet acquiring
dense and pixel-wise ground-truth is both labor-and time-consuming. Coarse annotations …
dense and pixel-wise ground-truth is both labor-and time-consuming. Coarse annotations …