CIT: Rethinking class-incremental semantic segmentation with a Class Independent Transformation
Open Access
- 26 April 2025
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 167
Abstract
No abstract availableAll Related Versions
Funding Information
- University of Adelaide
- China Scholarship Council (202008330289)
This publication has 27 references indexed in Scilit:
- GAN based augmentation using a hybrid loss function for dermoscopy imagesArtificial Intelligence Review, 2024
- SegViT v2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision TransformersInternational Journal of Computer Vision, 2023
- Comparison of the impacts of dermoscopy image augmentation methods on skin cancer classification and a new augmentation method with wavelet packetsInternational Journal of Imaging Systems and Technology, 2023
- SATS: Self-attention transfer for continual semantic segmentationPattern Recognition, 2023
- iCaRL: Incremental Classifier and Representation Learning2017
- Scene Parsing through ADE20K Dataset2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences of the United States of America, 2017
- Fully convolutional networks for semantic segmentation2015
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Catastrophic forgetting in connectionist networksTrends in Cognitive Sciences, 1999