> For the complete documentation index, see [llms.txt](https://zestyoreo9.gitbook.io/deep-learning-and-neural-networks/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://zestyoreo9.gitbook.io/deep-learning-and-neural-networks/one-shot-learning-project/papers.md).

# Papers

Week 1

| Title                                                                    | Link                                                                                                                                                                                                       | Comments after the first read/glance                                                                                                                                                                                                                 | Worthy? |
| ------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
| Generative One-Shot Face Recognition                                     | <https://arxiv.org/pdf/1910.04860.pdf>                                                                                                                                                                     | A mix of GANs and one-shot techniques to get better accuracy on face recog.                                                                                                                                                                          | YES     |
| Data-specific Adaptive Threshold for Face Recognition and Authentication | <https://arxiv.org/pdf/1810.11160v1.pdf>                                                                                                                                                                   | Good Approach for the threshold selection. But unsure if helpful for oneshot.                                                                                                                                                                        | YES     |
| Siamese Neural Networks for One-shot Image Recognition                   | <p><a href="https://www.cs.cmu.edu/~rsalakhu/papers/oneshot1.pdf"><https://www.cs.cmu.edu/~rsalakhu/papers></a></p><p><a href="https://www.cs.cmu.edu/~rsalakhu/papers/oneshot1.pdf">/oneshot1.pdf</a></p> | Discusss the siamese network for character recog in detail. This is the idea behind face recog. But isnt worth looking into for our project's goals.                                                                                                 | NO      |
| FaceNet: A Unified Embedding for Face Recognition and Clustering         | <https://arxiv.org/pdf/1503.03832v3.pdf>                                                                                                                                                                   | The SOTA face recog model for now in the world. Used Triplet Loss function for training                                                                                                                                                              | YES     |
| Deep Polynomial Neural Networks                                          | <https://arxiv.org/pdf/2006.13026v2.pdf>                                                                                                                                                                   | Nice paper which discusses the use of only linear activation functions to learn patterns. But is not very relevant (it is an all new approach which we can try after trying traditional non-linear act. functions first) to the problem at hand (FR) | NO      |
| SphereFace: Deep Hypersphere Embedding for Face Recognition              | <https://arxiv.org/pdf/1704.08063.pdf>                                                                                                                                                                     | Awesome paper which discusses a radical and awesome new method to train FR systems.                                                                                                                                                                  | YES     |

#### Survey Paper on Face Recognition Model Papers : <https://arxiv.org/pdf/1804.06655.pdf>

#### Useful Blogpost : <https://machinelearningmastery.com/one-shot-learning-with-siamese-networks-contrastive-and-triplet-loss-for-face-recognition/>

#### Video on ArcFace : <https://www.youtube.com/watch?v=H1qEp_czI1I&ab_channel=platformai>

### Papers To Read

* [ ] VGGFace2 : <https://arxiv.org/pdf/1710.08092.pdf>
* [ ] NormFace : <https://arxiv.org/abs/1704.06369>
* [ ] ArcFace : <https://arxiv.org/pdf/1801.07698.pdf>