Adversarial Loss
الخسارة التنافسية
دالة خسارة تستخدم شبكة مُميِّز تنافسي لتقييم واقعية المخرجات، فتدفع النموذج لإنتاج صور حادة وطبيعية المظهر.
A loss function using an adversarial discriminator network to evaluate output realism, pushing the model to produce sharp, natural-looking images.
Also translated asالخسارة العدائية، خسارة المُميِّز
First appears in this corpus in: Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks (2017)
Appears in these papers
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017in the sky ✦
- High-Resolution Image Synthesis with Latent Diffusion Models2022in the sky ✦
- Image-to-Image Translation with Conditional Adversarial Networks2017in the sky ✦
- Image-to-Image Translation with Conditional Adversarial Networks2017in the sky ✦