Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation
Sign Up to like & getrecommendations! Published in 2021 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.1109/tpami.2021.3133954
Abstract: Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform poorly when they are… read more here.
Keywords: background incremental; semantic segmentation; modeling background; segmentation modeling ... See more keywords