Research map / Label-efficient and robust learning / Recognition and long-tail
OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations
Check 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 |
|---|---|---|---|
| Constrain the latent space and train with latent and visual discriminators plus informative-negative mining | OCGAN · MNIST, Protocol 1 | AUC: 0.932 -> 0.977 | Helped |
| Constrain the latent space and train with latent and visual discriminators plus informative-negative mining | OCGAN · COIL100, Protocol 1 | AUC: 0.968 -> 0.995 | Helped |
| Constrain the latent space and train with latent and visual discriminators plus informative-negative mining | OCGAN · fMNIST, Protocol 1 | AUC: 0.908 -> 0.924 | Helped |
| Constrain the latent space and train with latent and visual discriminators plus informative-negative mining | OCGAN · MNIST, Protocol 2 | mean AUC: 0.9696 -> 0.9750 | Helped |
| Constrain the latent space and train with latent and visual discriminators plus informative-negative mining | OCGAN · CIFAR10, Protocol 2 | mean AUC: 0.6481 -> 0.6566 | Helped |
| Add the latent discriminator (ablation) | Auto-encoder only · MNIST | mean AUC: 0.957 -> 0.959 | Helped |
| Add the visual discriminator alongside the latent discriminator (ablation) | Auto-encoder with latent discriminator · MNIST | mean AUC: 0.959 -> 0.971 | Helped |
| Add informative-negative mining using the classifier (ablation) | Auto-encoder with two discriminators · MNIST | mean AUC: 0.971 -> 0.975 | Helped |
Closest papers by meaning
- Adversarially Learned One-Class Classifier for Novelty Detection (CVPR 2018 · similarity 0.91)
- Generative Probabilistic Novelty Detection with Adversarial Autoencoders (NeurIPS 2018 · similarity 0.88)
- RareGAN: Generating Samples for Rare Classes (AAAI 2022 · similarity 0.88)
- Fake It Until You Make It : Towards Accurate Near-Distribution Novelty Detection (ICLR 2023 · similarity 0.87)
- GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification (ICLR 2020 · similarity 0.87)
- Old Is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm (CVPR 2020 · 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.