Research map / Label-efficient and robust learning / Recognition and long-tail
Generative-Discriminative Complementary Learning
Yanwu Xu, Mingming Gong, Junxiang Chen, Tongliang Liu, Kun Zhang, Kayhan Batmanghelich
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 |
|---|---|---|---|
| Use generative-discriminative CCGAN instead of discriminative DCL | Complementary-label classification · MNIST and CIFAR10, across tested sample sizes | test accuracy | Improved |
| Use generative-discriminative CCGAN instead of discriminative DCL | Complementary-label classification · CIFAR100 and VGGFACE100, across r_l values in Table 1 | accuracy | Improved |
| Use generative-discriminative CCGAN instead of DCL | Complementary-label classification · MNIST and CIFAR10, biased M | accuracy | Improved |
| Use generative-discriminative CCGAN instead of DCL | Complementary-label classification · CIFAR100 and VGGFACE100, biased M | accuracy | Improved |
| Increase the number of complementary labels per image (ablation) | CCGAN and DCL · MNIST | test accuracy | Improved |
| Use DCL rather than CCGAN when each image receives many complementary labels (ablation) | Complementary-label classification · MNIST, many complementary labels per image | test accuracy | Mixed |
| Add unlabeled data to estimate the data marginal in SCCGAN (ablation) | CCGAN · MNIST | test accuracy | Improved |
Closest papers by meaning
- Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms (TPAMI 2022 · similarity 0.89)
- Dual Projection Generative Adversarial Networks for Conditional Image Generation (ICCV 2021 · similarity 0.88)
- CcGAN: Continuous Conditional Generative Adversarial Networks for Image Generation (ICLR 2021 · similarity 0.88)
- Discriminative Complementary-Label Learning with Weighted Loss (ICML 2021 · similarity 0.88)
- Conditional GANs with Auxiliary Discriminative Classifier (ICML 2022 · similarity 0.88)
- Fusing Conditional Submodular GAN and Programmatic Weak Supervision (AAAI 2024 · similarity 0.87)
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.
