2020CVPR-ZSL论文源码合辑(持续更新中)
- 《Detailed Broadly Generalized Zero-Shot Learning Paradigm: Underlying Dense Attribute-Based Attention》

论文地址:http://khoury.neu.edu/home/eelhami/publications/FineGrainedZSL-CVPR20.pdf
github:https://github.com/hbdat/cvpr20_DAZLE
2 《ZeroQ: A Novel Zero Shot Quantization Framework》

论文地址:https://arxiv.org/pdf/2001.00281.pdf
github:https://github.com/amirgholami/ZeroQ
3 《A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning》

github:
4 《Hyperbolic Visual Embedding Learning for Zero-Shot Recognition》

论文链接:http://openaccess.thecvf.com/content_CVPR_2020/papers/Liu_Hyperbolic_Visual Embedding Learning for Zero-Shot Recognition CVPR 2020 Paper.pdf
github:https://github.com/ShaoTengLiu/Hyperbolic_ZSL
- 《Identifying human object interactions through the framework of zero-shot learning》

论文链接:http://openaccess.thecvf.com/content\_CVPR\_2020/papers/Wang\_Discovering\_Human\_Interactions\_With\_Novel\_Objects\_via_Zero-Shot\_Learning CVPR 2020 paper.pdf
该研究详细探讨了基于零样本学习技术的内容部分
github:https://github.com/scwangdyd/zero_shot_hoi
6 《Generalized Zero-Shot Learning Via Over-Complete Distribution》

论文地址:https://arxiv.org/pdf/2004.00666.pdf
github:
7 《Extracting Redundancy-free Features: A Comprehensive Approach to Generalized Zero-Shot Object Recognition》

论文地址:https://arxiv.org/pdf/2006.08939.pdf
github:
- 《Domain-sensitive Bias Mitigation in Visual Domains for Generalizable Zero-Shot Learning》

论文地址:https://arxiv.org/pdf/2003.13261.pdf
github:https://github.com/mboboGO/DVBE
9 《Re-examining Zero-shot Video-based Classification Task: End-to-end Training for Realistic Application》

论文地址:https://arxiv.org/pdf/2003.01455.pdf
github:https://github.com/bbrattoli/ZeroShotVideoClassification
编号:(10)自监督领域感知的生成网络用于泛化零样本学习

github:
11 《Episode-based Prototype Generating Network for Zero-Shot Learning》

论文地址:https://arxiv.org/pdf/1909.03360.pdf
github:https://github.com/yunlongyu/EPGN
12 《Don’t Even Look Once: Synthesizing Features for Zero-Shot Detection》

论文链接
github:
深入研究了2020年CVPR上有关Zero-Suppressed Learning(ZSL)的相关论文。目前仍在持续深入学习这一领域,并期待与大家一起交流分享,并共同完善这一方向的研究工作
