Disentangled Representation
التمثيل المُفكَّك
تمثيل كامن يلتقط فيه كل بُعد عامل تغيُّر مستقل واحد في البيانات (مثل اللون أو الحجم أو الزاوية)، مما يتيح التحكم الدقيق في التوليد.
A latent representation where each dimension captures a single independent factor of variation in the data (e.g. color, size, angle), enabling fine-grained control over generation.
Also translated asالتمثيل المُفصول، تمثيل العوامل المستقلة
First appears in this corpus in: Representation Learning: A Review and New Perspectives (2013)
Appears in these papers
- beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework2017in the sky ✦
- beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework2017in the sky ✦
- Representation Learning: A Review and New Perspectives2013in the sky ✦
- Representation Learning: A Review and New Perspectives2013in the sky ✦
- A Style-Based Generator Architecture for Generative Adversarial Networks2019in the sky ✦
- A Style-Based Generator Architecture for Generative Adversarial Networks2019in the sky ✦