Porównaj metody
Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.
| Wyjaśnialne GAN (Explainable GAN)× | Model dyfuzyjny× | |
|---|---|---|
| Dziedzina | Uczenie głębokie | Uczenie głębokie |
| Rodzina | Machine learning | Machine learning |
| Rok powstania≠ | 2019 (GAN Dissection); ongoing | 2020 |
| Twórca≠ | Bau, D. et al. (GAN Dissection); broader XAI-GAN community | Ho, J., Jain, A. & Abbeel, P. |
| Typ≠ | Explainable generative model | Generative deep learning (denoising diffusion) |
| Źródło pierwotne≠ | Bau, D., Zhu, J.-Y., Strobelt, H., Zhou, B., Tenenbaum, J. B., Freeman, W. T., & Torralba, A. (2019). GAN Dissection: Visualizing and Understanding Generative Adversarial Networks. In Proceedings of the International Conference on Learning Representations (ICLR 2019). link ↗ | Ho, J., Jain, A. & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. NeurIPS. link ↗ |
| Inne nazwy≠ | XAI-GAN, Interpretable GAN, Transparent GAN, Explainable Generative Model | Difüzyon Modeli (DDPM / Stable Diffusion), difüzyon modeli, denoising diffusion model, DDPM |
| Pokrewne | 4 | 4 |
| Podsumowanie≠ | Explainable GAN applies interpretability techniques to Generative Adversarial Networks to reveal which internal units and latent directions cause specific visual or structural features in generated outputs. It combines GAN training with post-hoc analysis tools — such as unit dissection, saliency maps, or disentangled latent spaces — to make generative model behaviour transparent and auditable. | A diffusion model is a generative deep-learning method, introduced by Ho, Jain and Abbeel in 2020 (DDPM), that learns to produce high-quality images, audio and molecular structures by reversing a step-by-step noising process. It has largely displaced GANs as the current state of the art in generative modelling. |
| ScholarGateZbiór danych ↗ |
|
|