Class: Neural Network And Deep Learning (Graduate Class, Dept. of Data Science, SNUT)
Professor: Sangheum Hwang
Semester: Fall
| Students Number | Name |
|---|---|
| 18512083 | Jihyo Kim |
| 19510099 | Hongjea Park |
| 19510101 | Geongyu Lee |
| 19512024 | Sohee Ha |
| Classes | Images | Objects |
|---|---|---|
| Aeroplane | 116 | 136 |
| Bicycle | 97 | 124 |
| Bird | 136 | 176 |
| Boat | 106 | 153 |
| Bottle | 117 | 176 |
| Bus | 99 | 147 |
| Car | 161 | 276 |
| Cat | 169 | 195 |
| Chair | 170 | 348 |
| Cow | 82 | 161 |
| Diningtable | 104 | 108 |
| Dog | 156 | 194 |
| Horse | 105 | 136 |
| Motorbike | 103 | 126 |
| Person | 526 | 925 |
| Pottedplant | 115 | 209 |
| Sheep | 83 | 209 |
| Sofa | 117 | 138 |
| Train | 106 | 118 |
| Tvmonitor | 113 | 148 |
| Total | 1928 | 4203 |
| Base | Adversarial | |
|---|---|---|
| baseline | ||
| label smoothing | ||
| cut-out | ||
| label smoothing + cut-out |
[DOG]
[HUMAN]
- Pre-Trainied 모델로 학습
- Adversarial Training을 통하여 얻는 이득에 비하여 얼마나 이득이 있었는지 계산하기
- Performence measure 추가 하기
@misc{pascal-voc-2010, author = "Everingham, M. and Van~Gool, L. and Williams, C. K. I. and Winn, J. and Zisserman, A.", title = "The {PASCAL} {V}isual {O}bject {C}lasses {C}hallenge 2010 {(VOC2010)} {R}esults", howpublished = "http://www.pascal-network.org/challenges/VOC/voc2010/workshop/index.html"}
[1] Goibert, M., & Dohmatob, E. (2019). Adversarial Robustness via Adversarial Label-Smoothing. arXiv preprint arXiv:1906.11567.
[2] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
[3] Ronneberger, O., Fischer, P., & Brox, T. (2015, October). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention (pp. 234-241). Springer, Cham.
[4] Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014). Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572.
[5] Müller, R., Kornblith, S., & Hinton, G. (2019). When Does Label Smoothing Help?. arXiv preprint arXiv:1906.02629.
[6] DeVries, T., & Taylor, G. W. (2017). Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552.