Hugging Face's logo

Idiap
/
EdgeFace-Base

Model card Files Community
Idiap-Data commited on
Commit
52017b6
·
verified ·
1 Parent(s): 33be5dc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +75 -3
README.md CHANGED
@@ -1,3 +1,75 @@
1
- ---
2
- license: cc-by-nc-sa-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ ---
4
+
5
+
6
+ # EdgeFace-Base
7
+
8
+ We present EdgeFace- a lightweight and efficient face recognition network inspired by the hybrid architecture of EdgeNeXt. By effectively combining the strengths of both CNN and Transformer models, and a low rank linear layer, EdgeFace achieves excellent face recognition performance optimized for edge devices. The proposed EdgeFace network not only maintains low computational costs and compact storage, but also achieves high face recognition accuracy, making it suitable for deployment on edge devices. The proposed EdgeFace model achieved the top ranking among models with fewer than 2M parameters in the IJCB 2023 Efficient Face Recognition Competition. Extensive experiments on challenging benchmark face datasets demonstrate the effectiveness and efficiency of EdgeFace in comparison to state-of-the-art lightweight models and deep face recognition models. Our EdgeFace model with 1.77M parameters achieves state of the art results on LFW (99.73%), IJB-B (92.67%), and IJB-C (94.85%), outperforming other efficient models with larger computational complexities. The code to replicate the experiments will be made available publicly.
9
+
10
+
11
+ ## Overview
12
+
13
+ * **Training**: EdgeFace-Base was trained on [Webface260M](https://www.face-benchmark.org/) dataset (12M and 4M subsets)
14
+ * **Parameters**: 18.23M
15
+ * **Task**: Zero-shot Multi-speaker TTS
16
+ * **Output structure**: Batch of face images
17
+
18
+ ## Evaluation of EdgeFace
19
+
20
+ ![Edge Face](https://gitlab.idiap.ch/bob/bob.paper.tbiom2023_edgeface/-/raw/master/assets/edgeface.png)
21
+
22
+ | Model | MPARAMS | MFLOPs | LFW (%) | CA-LFW (%) | CP-LFW (%) | CFP-FP (%) | AgeDB-30 (%) | IJB-B (%) | IJB-C (%) |
23
+ |------------------------------|---------|-----------|--------------|--------------|--------------|--------------|--------------|-----------|-----------|
24
+ | VarGFaceNet | 5.0 | 1022 | 99.85 | 95.15 | 88.55 | 98.50 | 98.15 | 92.9 | 94.7 |
25
+ | ShuffleFaceNet 2× | 4.5 | 1050 | 99.62 | - | - | 97.56 | 97.28 | - | - |
26
+ | MixFaceNet-M | 3.95 | 626.1 | 99.68 | - | - | - | 97.05 | 91.55 | 93.42 |
27
+ | ShuffleMixFaceNet-M | 3.95 | 626.1 | 99.60 | - | - | - | 96.98 | 91.47 | 91.47 |
28
+ | MobileFaceNetV1 | 3.4 | 1100 | 99.4 | 94.47 | 87.17 | 95.8 | 96.4 | 92.0 | 93.9 |
29
+ | ProxylessFaceNAS | 3.2 | 900 | 99.2 | 92.55 | 84.17 | 94.7 | 94.4 | 87.1 | 89.7 |
30
+ | MixFaceNet-S | 3.07 | 451.7 | 99.6 | - | - | - | 96.63 | 90.17 | 92.30 |
31
+ | ShuffleMixFaceNet-S | 3.07 | 451.7 | 99.58 | - | - | - | 97.05 | 90.94 | 93.08 |
32
+ | ShuffleFaceNet 1.5x | 2.6 | 577.5 | 99.7 | 95.05 | 88.50 | 96.9 | 97.3 | 92.3 | 94.3 |
33
+ | MobileFaceNet | 2.0 | 933 | 99.7 | 95.2 | 89.22 | 96.9 | 97.6 | 92.8 | 94.7 |
34
+ | PocketNetM-256 | 1.75 | 1099.15 | 99.58 | 95.63 | 90.03 | 95.66 | 97.17 | 90.74 | 92.70 |
35
+ | PocketNetM-128 | 1.68 | 1099.02 | 99.65 | 95.67 | 90.00 | 95.07 | 96.78 | 90.63 | 92.63 |
36
+ | MixFaceNet-XS | 1.04 | 161.9 | 99.60 | - | - | - | 95.85 | 88.48 | 90.73 |
37
+ | ShuffleMixFaceNet-XS | 1.04 | 161.9 | 99.53 | - | - | - | 95.62 | 87.86 | 90.43 |
38
+ | MobileFaceNets | 0.99 | 439.8 | 99.55 | - | - | - | 96.07 | - | - |
39
+ | PocketNetS-256 | 0.99 | 587.24 | 99.66 | 95.50 | 88.93 | 93.34 | 96.35 | 89.31 | 91.33 |
40
+ | PocketNetS-128 | 0.92 | 587.11 | 99.58 | 95.48 | 89.63 | 94.21 | 96.10 | 89.44 | 91.62 |
41
+ | ShuffleFaceNet 0.5x | 0.5 | 66.9 | 99.23 | - | - | 92.59 | 93.22 | - | - |
42
+ | EdgeFace-S(γ = 0.5)(ours) | 3.65 | 306.11 | 99.78 | 95.71 | 92.56 | 95.81 | 96.93 | 93.58 | 95.63 |
43
+ | EdgeFace-XS(γ = 0.6)(ours) | 1.77 | 154 | 99.73 | 95.28 | 91.82 | 94.37 | 96.00 | 92.67 | 94.8 |
44
+ | Edgeface_XXS (ours) | 1.24 | 94.72 | 99.57 ± 0.33 | 94.83 ± 0.98 | 90.27 ± 0.93 | 93.63 ± 0.99 | 94.92 ± 1.15 |- | - |
45
+ |**Edgeface_Base (ours)** | 18.23 | 1398.83 | 99.83 ± 0.24 | 96.07 ± 1.03 | 93.75 ± 1.16 | 97.01 ± 0.94 | 97.60 ± 0.70 |- | - |
46
+
47
+
48
+ #### Performance benchmarks of different variants of **EdgeFace**:
49
+
50
+ | Model | MPARAMS | MFLOPs | LFW (%) | CALFW (%) | CPLFW (%) | CFP-FP (%) | AgeDB30 (%) |
51
+ |-------------------------|---------|---------|----------------|----------------|----------------|----------------|----------------|
52
+ |**edgeface_base** | 18.23 | 1398.83 | 99.83 ± 0.24 | 96.07 ± 1.03 | 93.75 ± 1.16 | 97.01 ± 0.94 | 97.60 ± 0.70 |
53
+ | edgeface_s_gamma_05 | 3.65 | 306.12 | 99.78 ± 0.27 | 95.55 ± 1.05 | 92.48 ± 1.42 | 95.74 ± 1.09 | 97.03 ± 0.85 |
54
+ | edgeface_xs_gamma_06 | 1.77 | 154.00 | 99.73 ± 0.35 | 95.28 ± 1.37 | 91.58 ± 1.42 | 94.71 ± 1.07 | 96.08 ± 0.95 |
55
+ | edgeface_xxs | 1.24 | 94.72 | 99.57 ± 0.33 | 94.83 ± 0.98 | 90.27 ± 0.93 | 93.63 ± 0.99 | 94.92 ± 1.15 |
56
+
57
+
58
+
59
+ ## Running kNN-TTS
60
+
61
+ Please check the project [GitHub repository](https://gitlab.idiap.ch/bob/bob.paper.tbiom2023_edgeface/)
62
+
63
+ ## License
64
+
65
+ EdgeFace is released under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en)
66
+
67
+
68
+
69
+ ## Citation
70
+
71
+ If you find our work useful, please cite the following publication:
72
+
73
+ ```
74
+
75
+ ```