# (7/19)Computer Vision recent Paper :FaceNet
###### tags: `paper`
[toc]
---
## Before Meeting
:::success
### Author:
- Florian Schroff
- 
- [refer](https://scholar.google.com/citations?user=eWbZJlMAAAAJ&hl=zh-TW)
- Dmitry Kalenichenko
- 
- [refer]()
- James Philbin
- 
- [refer](https://scholar.google.com/citations?user=80JxPpUAAAAJ&hl=en)
:::
[refer]()
[refer]()
[refer]()
---
## Recent Paper
---
### FaceNet: A Unified Embedding for Face Recognition and Clustering
:::success
#### Abstracion
- FaceNet
- directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure of face similarity
- deep convolutional network
- only 128-bytes per face.
- 
:::
:::info
#### Detail
- Introduction
- face verification (is this the same person)
- recognition (who is this person)
- clustering (find common people among these faces).
- face verification simply involves thresholding the distance between the two embeddings
- FaceNet directly trains its output to be a compact 128-D embedding using a tripletbased loss function based on LMNN
- consist of two matching face thumbnails and a non-matching face thumbnail and the loss aims to separate the positive pair from the negative by a distance margin
- online negative exemplar mining strategy
- Method
- end-to-end learning of the whole system
- triplet loss
- Triplet Loss
- 
- 
- 
- Triplet Selection
- Deep Convolutional Networks
- Stochastic Gradient Descent (SGD) with standard backprop [8, 11] and AdaGrad
- parameters
- FLOPS
- non-linear activation function
- The first category: adds 1×1×d convolutional layers
- The second category we use is based on GoogLeNet style Inception models
- 
- Datasets and Evaluation
- 
- 
- 
- Hold-out Test Set
- Personal Photos
- Academic Datasets
- Labeled Faces in the Wild (LFW
- Youtube Faces DB
:::
:::warning
#### Conclusion
- Experiments
- Computation Accuracy Trade-off
- 
- Computation Accuracy Trade-off
- 
- 
- Embedding Dimensionality
- each face is compactly represented by a 128 dimensional byte vector, which is ideal for large scale clustering and recognition
- Amount of Training Data
- the effect may be even larger on larger models
- 
- Effect of CNN Model
- Overall, in the final performance the top models of both architectures perform comparably. However, some of our Inception based models, such as NN3, still achieve good performance while signif
- Sensitivity to Image Quality
- 
- Performance on Youtube Faces DB
- We use the average similarity of all pairs of the first one hundred frames that our face detector detects in each video.This gives us a classification accuracy of 95.12%±0.39.
- We use the average similarity of all pairs of the first one hundred frames that our face detector detects in each video.This gives us a classification accuracy of 95.12%±0.39.
- Performance on LFW
- We evaluate our model on LFW using the standard protocol for unrestricted, labeled outside data.
- Our model is evaluated in two modes:
- Fixed center crop of the LFW provided thumbnail.
- A proprietary face detector (similar to Picasa) is run on the provided LFW thumbnails. If it fails to align the face (this happens for two images), the LFW alignment is used
- Face Clustering
- Our compact embedding lends itself to be used in order to cluster a users personal photos into groups of people with the same identity.
- 
- We provide a method to directly learn an embedding into an Euclidean space for face verification
- only requires minimal alignment (tight crop around the face area)
:::
[refer]()
---
###
:::success
#### Abstracion
:::
:::info
#### Detail
:::
:::warning
#### Conclusion
:::
[refer]()
---
###
:::success
#### Abstracion
:::
:::info
#### Detail
:::
:::warning
#### Conclusion
:::
[refer]()
---###
:::success
#### Abstracion
:::
:::info
#### Detail
:::
:::warning
#### Conclusion
:::
[refer]()
---###
:::success
#### Abstracion
:::
:::info
#### Detail
:::
:::warning
#### Conclusion
:::
[refer]()
---###
:::success
#### Abstracion
:::
:::info
#### Detail
:::
:::warning
#### Conclusion
:::
[refer]()
---###
:::success
#### Abstracion
:::
:::info
#### Detail
:::
:::warning
#### Conclusion
:::
[refer]()
---