Image Classification on CIFAR-10 (test) (Adversarial Robustness)
86.43Clean AccuracyPang et al. (2020)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Pang et al. (2020)Backbone=WRN-34-202025.12 | 86.43 | — | 54.39 | |
| Qin et al. (2019)Backbone=WRN-40-82025.12 | 86.28 | — | 52.84 | |
| adv-comp-sumBackbone=WRN-70-162025.12 | 86.16 | 59.35 | 57.77 | |
| adv-comp-sumBackbone=WRN-34-202025.12 | 85.59 | 58.92 | 57.41 | |
| Wu, Xia, and Wang (2020)Backbone=WRN-34-102025.12 | 85.36 | — | 56.17 | |
| Gowal et al. (2020)Backbone=WRN-70-162025.12 | 85.34 | 57.9 | 57.05 | |
| Rice, Wong, and J. Zico Kolter (2020)Backbone=WRN-34-202025.12 | 85.34 | — | 53.42 | |
| Gowal et al. (2020)Backbone=WRN-34-202025.12 | 85.21 | 57.54 | 56.7 | |
| adv-comp-sumBackbone=WRN-28-102025.12 | 84.5 | 57.28 | 55.79 | |
| Gowal et al. (2020)Backbone=WRN-28-102025.12 | 84.33 | 55.92 | 55.19 |