Can divisive normalization explain uncrowding? Let's add recurrent procedure in DN process to see if it can tackle uncrowding problem
- scikit-image 0.16.2
- Generalized Divisive normalization, implementation : https://github.com/jorge-pessoa/pytorch-gdn
Ballé, J., Laparra, V., & Simoncelli, E. P. (2016). End-to-end optimized image compression. arXiv preprint arXiv:1611.01704.
- Object centric learning with slot attention, implementation: https://github.com/lucidrains/slot-attention
Locatello, F., Weissenborn, D., Unterthiner, T., Mahendran, A., Heigold, G., Uszkoreit, J., ... & Kipf, T. (2020). Object-Centric Learning with Slot Attention. arXiv preprint arXiv:2006.15055.
- Style Normalization and Restitution for Domain Generalization and Adaptation : https://github.com/microsoft/SNR
Jin, X., Lan, C., Zeng, W., & Chen, Z. (2021). Style Normalization and Restitution for DomainGeneralization and Adaptation. arXiv preprint arXiv:2101.00588.