完整搜尋頁面 →

尺度 s 要多大?

選讀・DLCV 02A・臉部辨識與度量學習 的補充資料(第 2/6 則)。主線不依賴這則補充;引用編號對應本頁底部的參考文獻。

導覽:本頁與本系列: 導覽:本頁與本系列

本頁內容

補充資料 · 6

  1. 對齊臉部:最小平方相似變換
  2. 尺度 s 要多大?
  3. 並排比較邊界損失:一個公式與它的特殊情況
  4. 一個類別不只一個中心:子中心、品質感知邊界與 Partial FC
  5. 量測極小的錯誤率
  6. 深度學習之前:Eigenfaces 與 Fisherfaces

論文導讀 · 3

  1. ArcFace(Deng 等人,CVPR 2019;TPAMI 2022)
  2. NIST FRVT Part 3:族群效應(Grother、Ngan 與 Hanaoka,2019)
  3. 現代觀點綜述導讀

電腦視覺深度學習

  1. 02 · 深度影像分類
  2. 03 · 物件偵測:從 R-CNN 到 DETR
  3. 09 · 深度影像復原:低階視覺
查看完整課程樹 →

這則補充說明為什麼正規化 softmax 需要尺度 ss,以及 CosFace 如何給它一個下界。

為什麼需要尺度。 特徵與權重都是單位長度時,每個 logit 都是 [−1,1][-1, 1] 內的餘弦。即使在最好的情況下,正確類別的 logit 是 1,其他每個類別的 logit 至少是 −1-1,所以正確類別的 softmax 機率最多是 e1/(e1+(C−1)e−1)e^{1}/(e^{1} + (C-1)e^{-1})。當 C=10,000C = 10{,}000 個類別時,這約是 7×10−47 \times 10^{-4}:無論角度排得多好,網路都無法讓損失變小,訓練就停滯了。NormFace 指出了這個問題,並證明正規化後需要有一個尺度參數 [11]。

CosFace 的下界。 假設每個類別學到的特徵都分佈在它的類別中心附近,並令 PWP_W 為類別中心期望的最小事後機率(softmax 對恰好位於中心 WjW_j 的特徵,給類別 jj 的機率)。CosFace 證明這需要 [13]

s≥C−1C ln⁡(C−1) PW1−PW,s \ge \frac{C - 1}{C} \, \ln \frac{(C - 1)\, P_W}{1 - P_W},

其中 CC 是類別數,ln⁡\ln 是自然對數。這個下界隨 CC(以對數的速度)以及所要求的信心 PWP_W 增加。

計算實例。 當 C=10,000C = 10{,}000 且 PW=0.9P_W = 0.9:9,99910,000ln⁡9,999×0.90.1=ln⁡(89,991)×0.9999≈11.4\frac{9{,}999}{10{,}000}\ln\frac{9{,}999 \times 0.9}{0.1} = \ln(89{,}991) \times 0.9999 \approx 11.4。當 C=100,000C = 100{,}000 且 PW=0.99P_W = 0.99,下界約為 16.1。CosFace 與 ArcFace 使用的 s=64s = 64 [13], [16] 遠高於這些下界。

程式碼 · Python · 7 行
import numpy as np

def s_lower_bound(C, P):
    return (C - 1) / C * np.log((C - 1) * P / (1 - P))

for C, P in [(10_000, 0.9), (100_000, 0.99)]:
    print(f"C = {C:7,d}, P_W = {P}: s >= {s_lower_bound(C, P):.1f}")

輸出

C =  10,000, P_W = 0.9: s >= 11.4
C = 100,000, P_W = 0.99: s >= 16.1

太小或太大。 如果 ss 低於下界,損失就降不到接近零,即使已經分得很開的樣本仍會持續得到梯度而被推來推去。如果 ss 非常大,softmax 就近乎硬性的最大值:機率很早就飽和到 0 或 1,大多數樣本不再貢獻梯度,訓練可能變得不穩定。實務上,ss 是針對特定類別數固定的超參數;尺度與邊界會互相影響,因為 s⋅ms \cdot m 決定了目標 logit 被降低多少。

參考文獻

  1. M. Wang and W. Deng, “Deep face recognition: A survey,” Neurocomputing, vol. 429, pp. 215–244, 2021. doi
  2. P. Grother, M. Ngan and K. Hanaoka, “Face Recognition Vendor Test (FRVT) Part 3: Demographic Effects,” NIST Interagency Report 8280, National Institute of Standards and Technology, 2019. doi
  3. National Institute of Standards and Technology, “Face Recognition Technology Evaluation (FRTE) 1:1 Verification,” evaluation web page, accessed 2026. NIST
  4. K. Zhang, Z. Zhang, Z. Li and Y. Qiao, “Joint face detection and alignment using multitask cascaded convolutional networks,” IEEE Signal Processing Letters, vol. 23, no. 10, pp. 1499–1503, 2016. doi
  5. J. Deng, J. Guo, E. Ververas, I. Kotsia and S. Zafeiriou, “RetinaFace: Single-shot multi-level face localisation in the wild,” in Proc. IEEE/CVF CVPR, 2020. CVF
  6. Y. Taigman, M. Yang, M. Ranzato and L. Wolf, “DeepFace: Closing the gap to human-level performance in face verification,” in Proc. IEEE CVPR, 2014. CVF
  7. F. Schroff, D. Kalenichenko and J. Philbin, “FaceNet: A unified embedding for face recognition and clustering,” in Proc. IEEE CVPR, 2015. CVF
  8. S. Chopra, R. Hadsell and Y. LeCun, “Learning a similarity metric discriminatively, with application to face verification,” in Proc. IEEE CVPR, vol. 1, pp. 539–546, 2005. doi
  9. R. Hadsell, S. Chopra and Y. LeCun, “Dimensionality reduction by learning an invariant mapping,” in Proc. IEEE CVPR, vol. 2, pp. 1735–1742, 2006. doi
  10. A. Hermans, L. Beyer and B. Leibe, “In defense of the triplet loss for person re-identification,” arXiv:1703.07737, 2017. arXiv
  11. F. Wang, X. Xiang, J. Cheng and A. L. Yuille, “NormFace: L2 hypersphere embedding for face verification,” in Proc. ACM International Conference on Multimedia, pp. 1041–1049, 2017. doi
  12. W. Liu, Y. Wen, Z. Yu, M. Li, B. Raj and L. Song, “SphereFace: Deep hypersphere embedding for face recognition,” in Proc. IEEE CVPR, 2017. CVF
  13. H. Wang, Y. Wang, Z. Zhou, X. Ji, D. Gong, J. Zhou, Z. Li and W. Liu, “CosFace: Large margin cosine loss for deep face recognition,” in Proc. IEEE/CVF CVPR, 2018. CVF
  14. F. Wang, J. Cheng, W. Liu and H. Liu, “Additive margin softmax for face verification,” IEEE Signal Processing Letters, vol. 25, no. 7, pp. 926–930, 2018. doi
  15. J. Deng, J. Guo, N. Xue and S. Zafeiriou, “ArcFace: Additive angular margin loss for deep face recognition,” in Proc. IEEE/CVF CVPR, 2019. CVF
  16. J. Deng, J. Guo, J. Yang, N. Xue, I. Kotsia and S. Zafeiriou, “ArcFace: Additive angular margin loss for deep face recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 10, pp. 5962–5979, 2022. doi
  17. Y. Wen, K. Zhang, Z. Li and Y. Qiao, “A discriminative feature learning approach for deep face recognition,” in Proc. ECCV, pp. 499–515, 2016. doi
  18. J. Deng, J. Guo, T. Liu, M. Gong and S. Zafeiriou, “Sub-center ArcFace: Boosting face recognition by large-scale noisy web faces,” in Proc. ECCV, pp. 741–757, 2020. doi
  19. Q. Meng, S. Zhao, Z. Huang and F. Zhou, “MagFace: A universal representation for face recognition and quality assessment,” in Proc. IEEE/CVF CVPR, 2021. CVF
  20. M. Kim, A. K. Jain and X. Liu, “AdaFace: Quality adaptive margin for face recognition,” in Proc. IEEE/CVF CVPR, 2022. CVF
  21. X. An, J. Deng, J. Guo, Z. Feng, X. Zhu, J. Yang and T. Liu, “Killing two birds with one stone: Efficient and robust training of face recognition CNNs by Partial FC,” in Proc. IEEE/CVF CVPR, 2022. CVF
  22. A. Martin, G. Doddington, T. Kamm, M. Ordowski and M. Przybocki, “The DET curve in assessment of detection task performance,” in Proc. Eurospeech, pp. 1895–1898, 1997. ISCA
  23. G. B. Huang, M. Mattar, T. Berg and E. Learned-Miller, “Labeled Faces in the Wild: A database for studying face recognition in unconstrained environments,” in Workshop on Faces in ‘Real-Life’ Images: Detection, Alignment, and Recognition, Marseille, 2008. HAL
  24. I. Kemelmacher-Shlizerman, S. M. Seitz, D. Miller and E. Brossard, “The MegaFace benchmark: 1 million faces for recognition at scale,” in Proc. IEEE CVPR, 2016. CVF
  25. University of Washington, “MegaFace and MF2: Million-scale face recognition,” project web page, accessed 2026. project page
  26. Y. Guo, L. Zhang, Y. Hu, X. He and J. Gao, “MS-Celeb-1M: A dataset and benchmark for large-scale face recognition,” in Proc. ECCV, pp. 87–102, 2016. doi
  27. C. Whitelam, E. Taborsky, A. Blanton, B. Maze, J. Adams, T. Miller, N. Kalka, A. K. Jain, J. A. Duncan, K. Allen, J. Cheney and P. Grother, “IARPA Janus Benchmark-B face dataset,” in Proc. IEEE CVPR Workshops, 2017. CVF
  28. B. Maze, J. Adams, J. A. Duncan, N. Kalka, T. Miller, C. Otto, A. K. Jain, W. T. Niggel, J. Anderson, J. Cheney and P. Grother, “IARPA Janus Benchmark – C: Face dataset and protocol,” in Proc. International Conference on Biometrics (ICB), pp. 158–165, 2018. doi
  29. Z. Zhu, G. Huang, J. Deng, Y. Ye, J. Huang, X. Chen, J. Zhu, T. Yang, J. Lu, D. Du and J. Zhou, “WebFace260M: A benchmark unveiling the power of million-scale deep face recognition,” in Proc. IEEE/CVF CVPR, 2021. CVF
  30. K. Peng, A. Mathur and A. Narayanan, “Mitigating dataset harms requires stewardship: Lessons from 1000 papers,” in Proc. NeurIPS Datasets and Benchmarks Track, 2021. proceedings
  31. G. Bae, M. de La Gorce, T. Baltrušaitis, C. Hewitt, D. Chen, J. Valentin, R. Cipolla and J. Shen, “DigiFace-1M: 1 million digital face images for face recognition,” in Proc. IEEE/CVF WACV, 2023. CVF
  32. M. Kim, F. Liu, A. Jain and X. Liu, “DCFace: Synthetic face generation with dual condition diffusion model,” in Proc. IEEE/CVF CVPR, 2023. CVF
  33. F. Boutros, V. Struc, J. Fierrez and N. Damer, “Synthetic data for face recognition: Current state and future prospects,” Image and Vision Computing, vol. 135, art. 104688, 2023. doi
  34. M. Wang, W. Deng, J. Hu, X. Tao and Y. Huang, “Racial Faces in the Wild: Reducing racial bias by information maximization adaptation network,” in Proc. IEEE/CVF ICCV, pp. 692–702, 2019. doi
  35. J. Buolamwini and T. Gebru, “Gender Shades: Intersectional accuracy disparities in commercial gender classification,” in Proc. Conference on Fairness, Accountability and Transparency, PMLR 81, pp. 77–91, 2018. PMLR
  36. P. Drozdowski, C. Rathgeb, A. Dantcheva, N. Damer and C. Busch, “Demographic bias in biometrics: A survey on an emerging challenge,” IEEE Transactions on Technology and Society, vol. 1, no. 2, pp. 89–103, 2020. doi
  37. Z. Yu, Y. Qin, X. Li, C. Zhao, Z. Lei and G. Zhao, “Deep learning for face anti-spoofing: A survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, pp. 5609–5631, 2023. doi
  38. European Commission, “What personal data is considered sensitive?,” data protection guidance referring to Article 9 of the GDPR, accessed 2026. European Commission
  39. European Commission, “AI Act” (Regulation (EU) 2024/1689), policy page, accessed 2026. European Commission
  40. M. Turk and A. Pentland, “Eigenfaces for recognition,” Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 71–86, 1991. doi
  41. P. N. Belhumeur, J. P. Hespanha and D. J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 711–720, 1997. doi