Key Paper

Wu Z, Xiong Y, Yu S X, et al. Unsupervised feature learning via non-parametric instance discrimination[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 3733-3742.

Untitled

主要是提出来NCE loss functionMemory Bank 的无监督框架

Zhuang C, Zhai A L, Yamins D. Local aggregation for unsupervised learning of visual embeddings[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019: 6002-6012.

Typecial framework:

<aside> 💡 Three Contrast Learning: SimCLR, MOCO, BYOL

Contrast Learning details 三大对比学习框架调研报告

Contrastive Learning Conclusion

CVPR 2022 Contrast Learning 对比学习调研

</aside>

Innovation

<aside> 💡 Positive and Negative Data

Improvements in data (Postive sample pair)对比学习数据方面改进

List of design of sample pair

Conclusion 总结

</aside>

NCE loss function