Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Adversarial Metric Learning
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 adversarial pairs to metric learning | AML · Vehicle | classification error rate: $.223\pm.032$ -> $.203\pm.021$ | Helped |
| Add adversarial pairs to metric learning | AML · German-Credit | classification error rate: $.273\pm.021$ -> $.251\pm.012$ | Helped |
| Add adversarial pairs to metric learning | AML · Image-Segment | classification error rate: $.026\pm.007$ -> $.024\pm.004$ | Helped |
| Add adversarial pairs to metric learning | AML · Isolet | classification error rate: $.032\pm.012$ -> $.029\pm.009$ | Helped |
| Add adversarial pairs to metric learning | AML · Letters | classification error rate: $.041\pm.027$ -> $.032\pm.020$ | Helped |
| Add adversarial pairs to metric learning | AML · MNIST | classification error rate: $.118\pm.012$ -> $.105\pm.001$ | Helped |
| Add adversarial pairs to metric learning | AML · Breast-Cancer | classification error rate: $.040\pm.015$ -> $.044\pm.001$ | Hurt |
| Increase the adversarial-data weight α within (0,1) (ablation) | AML · MNIST | test error | Helped |
| Set adversarial neighborhood parameter β around 0.8 (ablation) | AML · MNIST | test accuracy | Helped |
Closest papers by meaning
- Metric Learning for Adversarial Robustness (NeurIPS 2019 · similarity 0.89)
- Symmetrical Synthesis for Deep Metric Learning (AAAI 2020 · similarity 0.87)
- Provably Robust Metric Learning (NeurIPS 2020 · similarity 0.87)
- Unsupervised Metric Learning with Synthetic Examples (AAAI 2020 · similarity 0.87)
- Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks (AAAI 2024 · similarity 0.85)
- Revisiting Adversarial Training at Scale (CVPR 2024 · similarity 0.84)
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.