Region embedding with intra and inter-view contrastive learning
Unsupervised region representation learning aims to extract dense and effective features from unlabeled urban data. While some efforts have been made for solving this problem based on multiple views, existing methods are still insufficient in extracting representations in a view and/or incorporating...
Saved in:
Main Authors: | Zhang, Liang, Long, Cheng, Cong, Gao |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/172863 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Prototypical graph contrastive learning
by: LIN, Shuai, et al.
Published: (2022) -
MITIGATING FEATURE SUPPRESSION IN CONTRASTIVE LEARNING
by: ZHANG JIHAI
Published: (2024) -
BlendCSE: blend contrastive learnings for sentence embeddings with rich semantics and transferability
by: Xu, Jiahao, et al.
Published: (2024) -
Improving tail-class representation with centroid contrastive learning
by: Tiong, Anthony Meng Huat, et al.
Published: (2023) -
Multi-level transitional contrast learning for personalized image aesthetics assessment
by: Yang, Zhichao, et al.
Published: (2023)