Incremental learning technologies for semantic segmentation
Semantic segmentation models based on deep learning technologies have achieved remarkable results in recent years. However, many models encounter the problem of catastrophic forgetting, i.e. when the model is required to learn a new task without labels for old objects, its performance drops signific...
Saved in:
主要作者: | Yang, Yizhuo |
---|---|
其他作者: | Xie Lihua |
格式: | Thesis-Master by Coursework |
語言: | English |
出版: |
Nanyang Technological University
2022
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/157338 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Semantic segmentation of delayered IC images with shape-variant convolution
由: Wang, Xue
出版: (2022) -
Incremental Q-learning Partially Observable Markov Decision Process intraday trading system
由: Goh, Choon Tat.
出版: (2010) -
Towards coordinated multi-agent exploration problem via segmentation and reinforcement learning
由: Chen, Zichen
出版: (2020) -
A pseudo-incremental rough set-based pseudo outer-product with ensemble learning (ieRSPOP++) fuzzy neural network
由: Iyer, Aparna.
出版: (2013) -
A novel incremental rough set-based pseudo outer-product with ensemble learning (ieRSPOP) neuro-fuzzy system for forecasting volatility
由: Tor Das, Ronald.
出版: (2010)