> 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

| 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>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://zestyoreo9.gitbook.io/deep-learning-and-neural-networks/one-shot-learning-project/papers.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.