Research map / Adversarial robustness and security / Attacks on text and graphs
Revisiting Visual Model Robustness: A Frequency Long-Tailed Distribution View
Zhiyu Lin, Yifei Gao, Yunfan Yang, Jitao Sang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 BaSS | PGD-AT, ResNet-18 · CIFAR10 | AutoAttack accuracy: 48.90 -> 55.90 | Improved |
| add BaSS | PGD-AT, WRN-34 · CIFAR10 | AutoAttack accuracy: 51.98 -> 60.91 | Improved |
| add BaSS | TRADES, ResNet-18 · CIFAR10 | AutoAttack accuracy: 49.05 -> 56.27 | Improved |
| add BaSS | TRADES, WRN-34 · CIFAR10 | AutoAttack accuracy: 53.77 -> 62.69 | Improved |
| add BaSS | MART, ResNet-18 · CIFAR10 | AutoAttack accuracy: 49.48 -> 56.93 | Improved |
| add BaSS | MART, WRN-34 · CIFAR10 | AutoAttack accuracy: 51.42 -> 59.09 | Improved |
| add BaSS | PGD-AT, ResNet-18 · CIFAR100 | AutoAttack accuracy: 24.88 -> 27.95 | Improved |
| add BaSS | TRADES, WRN-34 · CIFAR100 | AutoAttack accuracy: 27.09 -> 33.03 | Improved |
| add BaSS | MART, ResNet-18 · CIFAR100 | AutoAttack accuracy: 26.26 -> 28.01 | Improved |
| add BaSS | PGD-AT, ResNet-50 · Restricted-ImageNet | AutoAttack accuracy: 33.37 -> 41.77 | Improved |
| add BaSS | TRADES, ResNet-50 · Restricted-ImageNet | AutoAttack accuracy: 35.50 -> 42.80 | Improved |
| add BaSS to AugMix | AugMix, WRN-40-2 · CIFAR10-C | Noise corruption accuracy: 84.62 -> 88.66 | Improved |
Closest papers by meaning
- Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain (NeurIPS 2022 · similarity 0.88)
- Fantastic Robustness Measures: The Secrets of Robust Generalization (NeurIPS 2023 · similarity 0.87)
- Adversarial Robustness Under Long-Tailed Distribution (CVPR 2021 · similarity 0.87)
- Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models (ECCV 2018 · similarity 0.87)
- Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models (ICLR 2024 · similarity 0.86)
- Rethinking Robustness of Model Attributions (AAAI 2024 · similarity 0.86)
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.
