Research map / Adversarial robustness and security / Certified and empirical robustness
Kernel-convoluted Deep Neural Networks with Data Augmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add KCM smoothing (0.01,5) to Mixup (ablation) | MIXUP · CIFAR-10 test | test accuracy: 96.11 -> 96.39 | Helped |
| add KCM smoothing (0.01,1) to Mixup (ablation) | MIXUP · CIFAR-100 test | test accuracy: 78.47 -> 79.12 | Helped |
| add KCM smoothing (0.01,5) to Mixup (ablation) | MIXUP · CIFAR-10 white-box FGSM | Top-1 test accuracy: 75.63 -> 78.24 | Helped |
| add KCM smoothing (0.01,5) to Mixup (ablation) | MIXUP · CIFAR-10 white-box I-FGSM | Top-1 test accuracy: 51.82 -> 56.07 | Helped |
| add KCM smoothing (0.01,5) to Mixup (ablation) | MIXUP · CIFAR-10 black-box FGSM | Top-1 test accuracy: 85.31 -> 85.79 | Helped |
| add KCM smoothing (0.01,5) to Mixup (ablation) | MIXUP · CIFAR-10 black-box I-FGSM | Top-1 test accuracy: 88.87 -> 89.11 | Helped |
| add KCM smoothing (0.01,1) to Mixup (ablation) | MIXUP · CIFAR-100 white-box FGSM | Top-1 test accuracy: 38.79 -> 39.65 | Helped |
| add KCM smoothing (0.01,1) to Mixup (ablation) | MIXUP · CIFAR-100 white-box I-FGSM | Top-1 test accuracy: 22.99 -> 25.17 | Helped |
| add KCM smoothing (0.01,1) to Mixup (ablation) | MIXUP · CIFAR-100 black-box FGSM | Top-1 test accuracy: 63.62 -> 63.79 | Helped |
| add KCM smoothing (0.01,1) to Mixup (ablation) | MIXUP · CIFAR-100 black-box I-FGSM | Top-1 test accuracy: 67.97 -> 68.06 | Helped |
| remove Mixup from KCM (ablation) | MIXUP + KCM · CIFAR-10 test | test accuracy: 96.39 -> 95.06 | Hurt |
| remove Mixup from KCM (ablation) | MIXUP + KCM · CIFAR-100 test | test accuracy: 79.12 -> 75.34 | Hurt |
Closest papers by meaning
- mixup: Beyond Empirical Risk Minimization (ICLR 2018 · similarity 0.90)
- How Does Mixup Help With Robustness and Generalization? (ICLR 2021 · similarity 0.89)
- Pushing Boundaries: Mixup's Influence on Neural Collapse (ICLR 2024 · similarity 0.86)
- Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN (AAAI 2024 · similarity 0.86)
- Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization (NeurIPS 2025 · similarity 0.85)
- Generalization in Kernel Regression Under Realistic Assumptions (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.