Context-sensitive zero-shot semantic segmentation model based on meta-learning
Sign Up to like & getrecommendations! Published in 2021 at "Neurocomputing"
DOI: 10.1016/j.neucom.2021.08.120
Abstract: Abstract The zero-shot semantic segmentation requires models with a strong image understanding ability. The majority of current solutions are based on direct mapping or generation. These schemes are effective in dealing with the zero-shot recognition,… read more here.
Keywords: shot semantic; meta learning; shot; zero shot ... See more keywords
Meta-Seg: A Generalized Meta-Learning Framework for Multi-Class Few-Shot Semantic Segmentation
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Access"
DOI: 10.1109/access.2019.2953465
Abstract: Semantic segmentation performs pixel-wise classification for given images, which can be widely used in autonomous driving, robotics, medical diagnostics and etc. The recent advanced approaches have witnessed rapid progress in semantic segmentation. However, these supervised… read more here.
Keywords: shot semantic; meta learning; meta seg; semantic segmentation ... See more keywords
Axial Assembled Correspondence Network for Few-Shot Semantic Segmentation
Sign Up to like & getrecommendations! Published in 2023 at "IEEE/CAA Journal of Automatica Sinica"
DOI: 10.1109/jas.2022.105863
Abstract: Few-shot semantic segmentation aims at training a model that can segment novel classes in a query image with only a few densely annotated support exemplars. It remains a challenge because of large intra-class variations between… read more here.
Keywords: assembled correspondence; axial assembled; segmentation; correspondence ... See more keywords
Texture based Prototypical Network for Few-Shot Semantic Segmentation of Forest Cover: Generalizing for Different Geographical Regions
Sign Up to like & getrecommendations! Published in 2022 at "Neurocomputing"
DOI: 10.48550/arxiv.2203.15687
Abstract: Forest plays a vital role in reducing greenhouse gas emissions and mitigating climate change besides maintaining the world's biodiversity. The existing satellite-based forest monitoring system utilizes supervised learning approaches that are limited to a particular… read more here.
Keywords: texture; segmentation; shot semantic; geographical regions ... See more keywords