Upgrade to Pro — share decks privately, control downloads, hide ads and more …

【授業スライド】AnonyMask

 【授業スライド】AnonyMask

慶應義塾⼤学 B4 和田唯我 / Yuiga Wada
授業『機械知能』のスライドです. (院先取り)

- About me
- Blog

Yuiga Wada (和田唯我)

October 05, 2022
Tweet

More Decks by Yuiga Wada (和田唯我)

Other Decks in Technology

Transcript

  1. AnonyMask XXXXXX Yuiga Wada YYYYY Seitaro Otsuki ZZZZZZ Yui Iioka

    Machine Intelligence Demonstration (Team-7) 1 https://github.com/OtsuKotsu/Anonymask
  2. AnonyMask : Remove Corporate Logo naturally • Background ◦ Huge

    cost to hide the logos ◦ Existing approaches result in unnatural images! • Our product : AnonyMask ◦ Detects the logo by the object detection model ◦ Masks it out and repaints masked region naturally 2
  3. Method : AnonyMask • Overall flow 1. Object detection 2.

    Masking & Reconstruction 3. Smoothing & Improving Resolution 3
  4. Method : AnonyMask YOLOv5 Masked Auto Encoder SwinIR 4

  5. Results : AnonyMask generates remarkably natural images 👀 5

  6. Demonstration https://drive.google.com/file/d/1n0Ir2d-zZ9MazjbOpYz54ibGo540elnH/view?usp=sharing 6

  7. Quantitative Result Recall Precision F-Score [email protected] [email protected]:0.95 val. 0.656 0.789

    0.716 0.732 0.507 test 0.653 0.779 0.710 0.728 0.500 7
  8. Thank you for listening Thank you for listening ! https://github.com/OtsuKotsu/Anonymask

    8
  9. Appendix : Method (1/4) • YOLO v5 ◦ Detects the

    position and type of objects ◦ Metrics : mAP (mean Average Precision) • Overall flow 1. Object detection 2. Masking & Reconstruction 3. Smoothing & Improving Resolution 9
  10. Appendix : Method (2/4) • Overall flow 1. Object detection

    2. Masking & Reconstruction 3. Smoothing & Improving Resolution • MAE [He+, CVPR22] ◦ Masks the logo and Reconstructs from surrounding pixels ◦ Metrics : MSE 10
  11. Appendix : Method (3/4) • Overall flow 1. Object detection

    2. Masking & Reconstruction 3. Smoothing & Improving Resolution • Gaussian filter ◦ Erases noise in an image ◦ Blurs images 11
  12. 12 Appendix : Method (4/4) • Overall flow 1. Object

    detection 2. Masking & Reconstruction 3. Smoothing & Improving Resolution • SwinIR [Liang+, ICCV21] ◦ Restores high-quality images from low-quality images
  13. Appendix : Dataset 13 QMUL-OpenLogo • 27,083 images from 352

    logo classes • Object-level Annotations Our split : https://hangsu0730.github.io/qmul-openlogo/ #Examples Training set 18752 Validation set 4165 Test set 4166
  14. Appendix : demo details (1/4) YOLOv5 MAE SwinIR Server Client

    https://XXXX:port 14
  15. Appendix : demo details (2/4) 15

  16. Appendix : demo details (3/4) 16

  17. Appendix : demo details (4/4) 17

  18. Reference 1. K. He, X. Chen, S. Xie, et al.,

    “Masked autoencoders are scalable vision learners,” CVPR, pp.16000–16009, 2022. 2. J. Liang, J. Cao, G. Sun, et al., “Swinir: Image restoration using swin transformer,” CVPR, pp.1833–1844, 2021. 3. G. Jocher, A. Chaurasia, A. Stoken, et al., “ultralytics/yolov5: v6.1 - TensorRT, TensorFlow Edge TPU and OpenVINO Export and Inference,” 2022. https://doi.org/10.5281/zenodo.6222936 18