KNOWLEDGE DISTILLATION AND SIAMESE NETWORK ADOPTION FOR SEMANTIC SEGMENTATION USING SEMI- SUPERVISED LEARNING
The demand for large amounts of labeled data and large computations is a common problem in semantic segmentation. Semi-supervised answers the problem by utilizing data without labels in the training process, but choosing the right method in the unsupervised learning process is a challenge in itself....
Saved in:
主要作者: | Abdurrohman, Harits |
---|---|
格式: | Theses |
語言: | Indonesia |
在線閱讀: | https://digilib.itb.ac.id/gdl/view/69104 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Semi-supervised semantic visualization for networked documents
由: ZHANG, Delvin Ce, et al.
出版: (2021) -
Distilled Siamese networks for visual tracking
由: SHEN, Jianbing, et al.
出版: (2022) -
Random shuffling data for hyperspectral image classification with Siamese and Knowledge Distillation Network
由: Yang, Zhen, et al.
出版: (2023) -
Weakly-supervised semantic segmentation
由: CHEN, Zhaozheng
出版: (2023) -
Self-supervised feature learning for semantic segmentation of overhead imagery
由: SINGH, Suriya, et al.
出版: (2018)