动机
解决（1）对比学习管道中的增强通常会扭曲人物图像中的判别线索（2）细粒度的局部特征人物图像尚未得到充分探索。
思路
方法
- 基于正则化的图自编码器在推荐算法中的应用 Application of graph auto-encoders based on regularization in recommendation algorithms
- 《Span-Based Joint Entity and Relation Extraction with Transformer Pre-Training》阅读笔记
- Predict potential miRNA-disease associations based on bounded nuclear norm regularization
- Identity-Guided Human Semantic Parsing for Person Re-Identification
- TIP2023 | Human Co-Parsing Guided Alignment for Occluded Person Re-Identification
- 神经网络优化篇：详解其他正则化方法（Other regularization methods）
- jumpserver连接ecs实例报错：UNREACHABLE! => {"changed": false, "msg": "Failed to connect to the host via ssh: ssh_exchange_identification: Connection closed by remote host", "unreachable": true
- GPT-1论文《Improving Language Understanding by Generative Pre-Training》解读
- ssh WARNING: REMOTE HOST IDENTIFICATION HAS CHANGED! 解决办法
- 神经网络优化篇：详解dropout 正则化（Dropout Regularization）
本栏目推荐文章